Suspension device
Abstract
This record has no abstract on file.
Term
Projected expiry 8 February 2028.
- Priority and filed
- Granted
- Today
- Projected expiry
18 claims: 13 independent, 5 dependent
- 1検査対象領域の多値画像を取得する撮像手段と、 検出対象画像中の検出すべき最低輝度値 又は最高輝度値 を第1閾値として設定する第1閾値設定手段と、 前記第1閾値設定手段により前記最低輝度値が前記第1閾値として設定される場合、 前記撮像手段により取得された前記多値画像から前記第1閾値より大きい輝度値を有する複数の画素を抽出し、抽出された該複数の画素の輝度値の連結性に基づいて 、検出対象となりうる 画素の集合体を特定 し、 前記第1閾値設定手段により前記最高輝度値が前記第1閾値として設定される場合、前記撮像手段により取得された前記多値画像から前記第1閾値より小さい輝度値を有する複数の画素を抽出し、抽出された該複数の画素の輝度値の連結性に基づいて、検出対象となりうる画素の集合体を特定 するラベリング処理を行うラベリング処理手段と、 該ラベリング処理手段により特定された画素の集合体に対して、前記第1閾値 と異なる 第2閾値を設定する第2閾値設定手段と、 前記第1閾値設定手段により前記最低輝度値が前記第1閾値として設定され、前記 第2閾値設定手段により設定された 前記第2閾値が前記第1閾値より大きい場合、 前記第2閾値より小さい輝度値のみからなる前記画素の集合体を 検出対象から削除し、 前記第1閾値設定手段により前記最高輝度値が前記第1閾値として設定され、前記第2閾値設定手段により設定された前記第2閾値が前記第1閾値より小さい場合、前記第2閾値より大きい輝度値のみからなる前記画素の集合体を検出対象から 削除する削除手段と を備え る ことを特徴とする画像検査装置。
- 2前記ラベリング処理手段により特定された画素の集合体を有するラベリング処理画像を表示する画像表示手段と、 前記第2閾値設定手段により設定された前記第2閾値より小さい又は大きい輝度値のみからなる画素の集合体が検出対象から削除されるように前記画像表示手段にて前記ラベリング処理画像の表示を更新する手段と を備え、 前記第2閾値が変更される都度、変更された前記第2閾値より小さい又は大きい輝度値のみからなる画素の集合体が検出対象から削除されるように前記ラベリング処理画像の表示が更新される請求項1記載の 画像検査装置。
- 3前 記第1閾 値の 入力を受け付ける入力受付手段を備え 、 前記第2閾値設定手段は、前記第1閾値に所定値を加算した値を前記第2閾値として設定する 請求項 1記 載の画像検査装置。
- 4前 記第 2 閾値の入力を受け付ける入力受付手段を備え、 前記第 1 閾値設定手段は、前記第 2 閾値 から 所定値を 減算 した値を前記第 1 閾値として設定する請求項1記載の画像検査装置。
- 5前 記第 1 閾値の入力を受け付ける入力受付手段を備え、 前記第 2 閾値設定手段は、前記第 1 閾値から所定値を減算した値を前記第 2 閾値として設定する請求項1記載の画像検査装置。
- 6前 記第 2 閾値の入力を受け付ける入力受付手段を備え、 前記第 1 閾値設定手段は、前記第 2 閾値 に 所定値を 加算 した値を前記第 1 閾値として設定する請求項 1 記載の画像検査装置。
- 7前記撮像手段により取得された前記多値画像に対して所定サイズのセグメントを設定するセグメント設定手段と、 該セグメント設定手段により設定された前記セグメントを所定の画素単位で移動させながら前記セグメント内の画素の平均輝度値を算出し、算出された該平均輝度値を有するセグメント画像を生成し、前記ラベリング処理手段に出力するセグメント画像生成手段と を備える請求項3乃至6のいずれか一項に 記載の画像検査装置。
- 8前記セグメントの前記所定サイズ及び移動の前記所定の画素単位は、前記入力受付手段で受け付ける請求項7 記載の画像検査装置。
- 9前記第1閾値設定手段は、第1閾値として最低輝度値を設定するか最高輝度値を設定するかをユーザにより選択可能に構成されていることを特徴とする請求項1乃至8のいずれか一項に 記載の画像検査装置。
- 10検査対象領域を撮像して多値画像を取得する画像取得工程と、 検出対象画像中の検出すべき最低輝度値 又は最高輝度値 を第1閾値として設定する第1閾値設定工程と、 前記第1閾値設定工程にて前記最低輝度値が前記第1閾値として設定される場合、 前記画像取得工程にて取得された前記多値画像から前記第1閾値より大きい輝度値を有する複数の画素を抽出し、抽出された該複数の画素の輝度値の連結性に基づいて 、検出対象となりうる 画素の集合体を特定 し、 前記第1閾値設定工程にて前記最高輝度値が前記第1閾値として設定される場合、前記画像取得工程にて取得された前記多値画像から前記第1閾値より小さい輝度値を有する複数の画素を抽出し、抽出された該複数の画素の輝度値の連結性に基づいて、検出対象となりうる画素の集合体を特定 するラベリング処理を行うラベリング処理工程と、 該ラベリング処理工程にて特定された画素の集合体に対して、前記第1閾値 と異なる 第2閾値を設定する第2閾値設定工程と、 前記第1閾値設定工程にて前記最低輝度値が前記第1閾値として設定され、前記 第2閾値設定工程にて設定された 前記第2閾値が前記第1閾値より大きい場合、 前記第2閾値より小さい輝度値のみからなる前記画素の集合体を 検出対象から削除し、 前記第1閾値設定工程にて前記最高輝度値が前記第1閾値として設定され、前記第2閾値設定工程にて設定された前記第2閾値が前記第1閾値より小さい場合、前記第2閾値より大きい輝度値のみからなる前記画素の集合体を検出対象から 削除する削除工程と を 含む ことを特徴とする画像検査方法。
- 11前記第1閾値の入力を受け付ける入力受付工程を含み、前記第2閾値設定工程にて、前記第1閾値に所定値を加算した値が前記第2閾値として設定される請求項10記載の 画像検査方法。
- 12前 記第2閾値の入力を受け付ける入力受付工程を 含み、前記第1閾値設定工程にて、前記第2閾値から所定値を減算した値が前記第1閾値として設定される請求項10 記載の画像検査方法。
- 13前 記第1閾値の入力を受け付ける入力受付工程を 含み 、前記第2閾値設定工程にて、前記第1閾値 から 所定値を 減算 した値が前記第2閾値として設定される請求項10記載の画像検査方法。
- 14前 記第2閾値の入力を受け付ける入力受付工程を 含み 、前記第1閾値設定工程にて、前記第2閾値 に 所定値を 加算 した値が前記第1閾値として設定される請求項10記載の画像検査方法。
- 15前記画像取得工程にて取得された前記多値画像に対して所定サイズのセグメントを設定するセグメント設定工程と、 該セグメント設定工程にて設定された前記セグメントを所定の画素単位で移動させながら前記セグメント内の画素の平均輝度値を算出し、算出された該平均輝度値を有するセグメント画像を生成し、前記ラベリング処理工程へと送るセグメント画像生成工程と を含む請求項11乃至14のいずれか一項に 記載の画像検査方法。
- 16前記セグメントの前記所定サイズ及び移動の前記所定の画素単位は、前記入力受付工程にて受け付ける請求項15 記載の画像検査方法。
- 17検査対象領域を撮像して多値画像を取得する画像取得処理と、 検出対象画像中の検出すべき最低輝度値又は最高輝度値を第1閾値として設定する第1閾値設定処理と、 前記第1閾値設定処理にて前記最低輝度値が前記第1閾値として設定される場合、前記画像取得処理にて取得された前記多値画像から前記第1閾値より大きい輝度値を有する複数の画素を抽出し、抽出された該複数の画素の輝度値の連結性に基づいて、検出対象となりうる画素の集合体を特定し、 前記第1閾値設定処理にて前記最高輝度値が前記第1閾値として設定される場合、前記画像取得処理にて取得された前記多値画像から前記第1閾値より小さい輝度値を有する複数の画素を抽出し、抽出された該複数の画素の輝度値の連結性に基づいて、検出対象となりうる画素の集合体を特定するラベリング処理と、 該ラベリング処理を行った後、前記第1閾値の設定変更の要求が有るか否かを判断する第1判断処理と、 該第1判断処理により、前記第1閾値の設定変更の要求が有ると判断された場合、前記第1閾値を再設定する第1閾値再設定処理と、 該第1閾値再設定処理を行った場合、前記ラベリング処理へと分岐する第1分岐処理と、 前記ラベリング処理にて特定された画素の集合体に対して、前記第1閾値とは異なる第2閾値を設定する第2閾値設定処理と、 前記第1閾値設定処理にて前記最低輝度値が前記第1閾値として設定され、前記第2閾値設定処理にて設定された前記第2閾値が前記第1閾値より大きい場合、前記第2閾値より小さい輝度値のみからなる前記画素の集合体を検出対象から削除し、 前記第1閾値設定処理により前記最高輝度値が前記第1閾値として設定され、前記第2閾値設定処理により設定された前記第2閾値が前記第1閾値より小さい場合、前記第2閾値より大きい輝度値のみからなる前記画素の集合体を検出対象から削除する削除処理と、 該削除処理を行った後、前記第2閾値の設定変更の要求が有るか否かを判断する第2判断処理と、 該第2判断処理により、前記第2閾値の設定変更の要求が有ると判断された場合、前記第2閾値を再設定する第2閾値再設定処理と、 該第2閾値再設定処理を行った場合、前記削除処理へと分岐する第2分岐処理と をコンピュータに実行させることを特徴とするコンピュータプログラム。
- 18前記画像取得処理にて取得された前記多値画像に対して所定サイズのセグメントを設定するセグメント設定処理と、 該セグメント設定処理にて設定された前記セグメントを所定の画素単位で移動させながら前記セグメント内の画素の平均輝度値を算出し、算出された該平均輝度値を有するセグメント画像を生成し、前記ラベリング処理の対象とするセグメント画像生成処理と、 該セグメント画像生成処理を行った後、前記セグメントのサイズ及び/又は移動の画素単位の設定変更の要求が有るか否かを判断する第3判断処理と、 該第3判断処理により、前記サイズ及び/又は前記移動の画素単位の設定変更の要求が有ると判断された場合、前記サイズ及び/又は前記移動の画素単位を再設定するセグメント再設定処理と、 該セグメント再設定処理を行った場合、前記セグメント画像生成処理へと分岐する第3分岐処理と をコンピュータに実行させる請求項17記載のコンピュータプログラム。
Independent claims18
48 paragraphs, as filed
The present invention removes noise, which is a non-detection object, from a multi-valued image obtained by imaging an inspection target area, and determines the presence or absence of defects such as blob (aggregate) -like scratches and stains, which are the detection objects. The present invention relates to an image inspection device for inspecting size, shape, etc., an image inspection method, and a computer program for executing each processing step of the image inspection method.
As a conventional example, the acquired multi-valued image data is binarized by one threshold value, and the image data after binarization is subjected to labeling processing to perform labeling processing that is less than a predetermined number of pixels. An image data processing device has been proposed that can remove even noise having a high brightness value when the area of the figure is small by removing the figure as noise (see, for example, Patent Document 1). Hereinafter, the object to be finally detected is referred to as a detection object, and the object to be removed as noise is referred to as a detection object.<patcit num="1"><text>Japanese Patent Application Laid-Open No. 06-083953</text></patcit>
<p> However, in the above-mentioned conventional example, the non-detection object having an area smaller than the detection object can be removed, but the non-detection object having an area larger than the detection object cannot be removed. In the conventional example, in order to remove a non-detection object having a larger area than the detection object, it is possible to change the binarization threshold value higher (or lower) than the maximum brightness value of the non-detection object. However, if there is an image portion having a brightness value lower (or higher) than the brightness value of the non-detection target in the brightness value of the detection target, the figure of the detection target is finely divided and detected. There is a problem that the correct characteristics of the object cannot be obtained. In some cases, the figure may be finely divided, making it indistinguishable from a non-detectable object having a small area.</p><p> Further, in the above-mentioned conventional example, when the figures to be detected have a small area and a plurality of figures are collectively present in a predetermined area, they are all judged to be noise and removed. Therefore, a plurality of target figures are combined into one. There is a problem that it cannot be detected as a figure.</p><p> The present invention has been made in view of the above problems, and it is desired to reliably remove a blob having a large area of a non-detection target as noise from a multi-valued image and to remove it as noise in the blob of the detection target. An image inspection device, an image inspection method, and an image inspection method capable of detecting a blob to be detected without dividing it even when a brightness value lower (or higher) than the brightness value of an object is present. The first purpose is to provide a computer program that executes each processing step.</p><p> Further, in addition to the above-mentioned first object, the present invention has a small area for detection, and even when a plurality of detection objects are collectively present in a predetermined area, a plurality of objects are included in one. It can be detected as a blob, and the second purpose is to improve the discriminating ability of the blob.</p>
<p> In order to achieve the first object, the image inspection apparatus according to the first invention includes an imaging means for acquiring a multi-valued image of an inspection target area and a minimum brightness value to be detected in the detection target image.<u style="single">Or the maximum brightness value</u>As the first threshold value setting means and<u style="single">When the minimum luminance value is set as the first threshold value by the first threshold value setting means,</u>A plurality of pixels having a brightness value larger than the first threshold value are extracted from the multi-valued image acquired by the imaging means, and based on the connectivity of the extracted brightness values of the plurality of pixels.<u style="single">, Can be detected</u>Identify a collection of pixels<u style="single">When the maximum brightness value is set as the first threshold value by the first threshold value setting means, a plurality of pixels having a brightness value smaller than the first threshold value are obtained from the multi-valued image acquired by the imaging means. Extract and identify an aggregate of pixels that can be detected based on the connectivity of the brightness values of the plurality of extracted pixels.</u>The first threshold value is obtained with respect to the labeling processing means for performing the labeling processing and the aggregate of pixels specified by the labeling processing means.<u style="single">Different from</u>A second threshold setting means for setting the second threshold, and<u style="single">The minimum luminance value is set as the first threshold value by the first threshold value setting means, and the first threshold value is set.</u>Set by the second threshold setting means<u style="single">When the second threshold value is larger than the first threshold value,</u>An aggregate of the pixels consisting only of brightness values smaller than the second threshold value.<u style="single">When it is deleted from the detection target, the maximum luminance value is set as the first threshold value by the first threshold value setting means, and the second threshold value set by the second threshold value setting means is smaller than the first threshold value, the above. An aggregate of the pixels consisting only of brightness values larger than the second threshold value is detected from the detection target.</u>With the deletion means to delete<u style="single">It is characterized by being prepared.</u></p><p> With such a configuration, the first threshold value setting means has the lowest luminance value to be detected in the image to be detected.<u style="single">Or the maximum brightness value</u>Is set as the first threshold value, and the labeling processing means has a brightness value larger than the first threshold value.<u style="single">Or a small brightness value</u>The second threshold value setting means is larger than the first threshold value by identifying an aggregate (blob) of all pixels including the non-detection target object and the detection target object having.<u style="single">Or small</u>The second threshold is set and the deletion means is smaller than the second threshold.<u style="single">Or big</u>A set of pixels consisting only of luminance values is deleted from the set of all pixels. As a result, from the multi-valued image, a blob consisting of only the luminance values having a large area to be undetected and smaller than the second threshold value.<u style="single">, Or a blob consisting only of brightness values greater than the second threshold</u>Is surely removed as noise, and the part with low brightness value in the blob to be detected<u style="single">Or high part</u>Can be detected without dividing the blob to be detected even when is present.</p><p> The image inspection apparatus according to the second invention is<u style="single">In the first invention, an image display means for displaying a labeling processed image having an aggregate of pixels specified by the labeling processing means, and a brightness value smaller or larger than the second threshold value set by the second threshold setting means. The image display means is provided with a means for updating the display of the labeling processed image so that an aggregate of pixels consisting of only two pixels is deleted from the detection target, and the change is made each time the second threshold value is changed. The display of the labeling processed image is updated so that an aggregate of pixels consisting only of brightness values smaller or larger than the second threshold value is deleted from the detection target.</u>。 </p><p> With such a configuration<u style="single">Each time the second threshold is changed, the display of the labeling processed image is updated so that the aggregate of pixels consisting only of the brightness values smaller or larger than the changed second threshold is deleted from the detection target. You can check the blobs to be deleted while looking at them, and it is possible to avoid accidental deletion.</u>。 </p><p> No.<u style="single">3</u>In the first invention, the image inspection apparatus according to the present invention provides an input receiving means for receiving the input of the first threshold value.<u style="single">Prepare</u>The second threshold value setting means preferably sets a value obtained by adding a predetermined value to the first threshold value as the second threshold value.</p><p> With such a configuration, when the user wants to detect only blobs having a brightness difference of a predetermined value or more with respect to the first threshold value input by the input receiving means, the second threshold value is automatically set, which is convenient. There is.</p><p> No.<u style="single">4</u>In the first invention, the image inspection apparatus according to the present invention provides an input receiving means for receiving the input of the second threshold value.<u style="single">Prepare</u>The first threshold value setting means preferably sets a value obtained by subtracting a predetermined value from the second threshold value as the first threshold value.</p><p> With such a configuration, the user inputs a second threshold value by the input receiving means, and a blob having a brightness value larger than the input second threshold value is detected, but the user has a first threshold value smaller than the second threshold value by a predetermined value. It is convenient because the first threshold value is automatically set when you want to identify and detect the blob with.</p><p> No.<u style="single">5</u>The image inspection apparatus according to the invention is the first<u style="single">1</u>In the present invention, it is preferable that the input receiving means for receiving the input of the first threshold value is provided, and the second threshold value setting means sets a value obtained by subtracting a predetermined value from the first threshold value as the second threshold value.</p><p> With such a configuration, when the user wants to detect only blobs having a brightness difference larger than a predetermined value with respect to the first threshold value input by the input receiving means, the second threshold value is automatically set, which is convenient. There is.</p><p> No.<u style="single">6</u>The image inspection apparatus according to the invention is the first<u style="single">1</u>In the present invention, the input receiving means for receiving the input of the second threshold value is provided.<u style="single">Prepare</u>The first threshold value setting means preferably sets a value obtained by adding a predetermined value to the second threshold value as the first threshold value.</p><p> With such a configuration, the user inputs a second threshold value by the input receiving means, and a blob having a brightness value larger than the input second threshold value is detected, but the user has a first threshold value larger than the second threshold value by a predetermined value. It is convenient because the first threshold value is automatically set when you want to identify and detect the blob with.</p><p> In order to achieve the second purpose,<u style="single">7</u>The image inspection apparatus according to the invention is the third to third.<u style="single">6</u>In any one of the inventions, a segment setting means for setting a segment of a predetermined size for the multi-valued image acquired by the imaging means and the segment set by the segment setting means are set in predetermined pixel units. A segment image generating means that calculates the average luminance value of the pixels in the segment while moving, generates a segment image having the calculated average luminance value, and outputs the segment image to the labeling processing means.<u style="single">Prepare</u>Is preferable.</p><p> With such a configuration, a segment image is generated with the average luminance value of all the pixels in the segment calculated while moving a segment of a predetermined size in a predetermined pixel unit (movement amount) as one pixel value, and the segment image is generated. By performing processing using two threshold values, even if the detection target has a small area and a plurality of detection objects are collectively present in a predetermined area, the plurality of objects are detected as one blob. It is possible to improve the discriminating ability of blobs.</p><p> No.<u style="single">8</u>The image inspection apparatus according to the invention is the first<u style="single">7</u>In the present invention, it is preferable that the predetermined size of the segment and the predetermined pixel unit of movement are received by the input receiving means.</p><p> With such a configuration, the user can freely set the segment size (number of pixels in the X and Y directions) and the amount of movement (number of pixels in the X and Y directions) to detect an object as one blob. It can be adjusted freely.</p><p><u style="single">In any one of the first to eighth inventions, the image inspection apparatus according to the ninth invention determines whether the first threshold value setting means sets the minimum luminance value or the maximum luminance value as the first threshold value. It is preferably configured so that it can be selected by the user.</u><u style="single"> Since it is possible to select the case where the minimum luminance value is set as the first threshold value and the case where the maximum luminance value is set as the first threshold value, it is possible to select a labeling process that is highly effective according to the situation of the image. it can.</u><u style="single"></u>The image inspection method according to the tenth invention includes an image acquisition step of capturing an inspection target area and acquiring a multi-valued image, and a minimum luminance value to be detected in the detection target image.<u style="single">Or the maximum brightness value</u>As the first threshold value setting process and<u style="single">When the minimum luminance value is set as the first threshold value in the first threshold value setting step,</u>A plurality of pixels having a brightness value larger than the first threshold value are extracted from the multi-valued image acquired in the image acquisition step, and based on the connectivity of the brightness values of the extracted plurality of pixels.<u style="single">, Can be detected</u>Identify a collection of pixels<u style="single">When the maximum brightness value is set as the first threshold value in the first threshold value setting step, a plurality of pixels having a brightness value smaller than the first threshold value from the multi-valued image acquired in the image acquisition step. Pixels are extracted, and an aggregate of pixels that can be detected is specified based on the connectivity of the brightness values of the extracted plurality of pixels.</u>The first threshold value is obtained for the labeling processing step of performing the labeling processing and the aggregate of pixels specified in the labeling processing step.<u style="single">Different from</u>The second threshold setting process for setting the second threshold and<u style="single">In the first threshold value setting step, the minimum luminance value is set as the first threshold value, and the above</u>Set in the second threshold setting process<u style="single">When the second threshold value is larger than the first threshold value,</u>An aggregate of the pixels consisting only of brightness values smaller than the second threshold value.<u style="single">When deleted from the detection target, the maximum luminance value is set as the first threshold value in the first threshold value setting step, and the second threshold value set in the second threshold value setting step is smaller than the first threshold value. , An aggregate of the pixels consisting only of a brightness value larger than the second threshold value is detected from the detection target.</u>Including the deletion process to delete<u style="single">Characterized by</u>。 </p><p> With such a configuration, the minimum brightness value to be detected in the image to be detected in the first threshold setting step.<u style="single">Or the maximum brightness value</u>Is set as the first threshold value and is larger than the first threshold value in the labeling processing process.<u style="single">Or small</u>An aggregate (blob) of pixels having a brightness value is identified and is larger than the first threshold value in the second threshold value setting step.<u style="single">Or small</u>A second threshold is set and is smaller than the second threshold in the deletion process<u style="single">Or big</u>A set of pixels consisting only of luminance values is deleted from the set of all pixels. As a result, from the multi-valued image, a blob consisting of only the luminance values having a large area to be undetected and smaller than the second threshold value<u style="single">Or a blob consisting only of brightness values greater than the second threshold</u>Is surely removed as noise, and the part with low brightness value in the blob to be detected<u style="single">Or high part</u>Can be detected without dividing the blob to be detected even when is present.</p><p> No.<u style="single">11</u>In the tenth invention, the image inspection method according to the present invention includes an input receiving step of accepting an input of the first threshold value, and a value obtained by adding a predetermined value to the first threshold value in the second threshold value setting step is the first value. 2 It is preferable to set it as a threshold value.</p><p> With such a configuration, when the user wants to detect only blobs having a brightness difference of a predetermined value or more with respect to the first threshold value input in the input reception process, the second threshold value is automatically set, which is convenient. There is sex.</p><p> No.<u style="single">12</u>In the tenth invention, the image inspection method according to the present invention includes an input receiving step of accepting an input of the second threshold value, and a value obtained by subtracting a predetermined value from the second threshold value in the first threshold value setting step is the first. It is preferably set as one threshold.</p><p> With such a configuration, the user inputs the second threshold value in the input reception process, and a blob having a brightness value larger than the input second threshold value is detected, but the user is the first one that is smaller than the second threshold value by a predetermined value. When it is desired to specify the blob by the threshold value and perform detection, the first threshold value is automatically set, which is convenient.</p><p> No.<u style="single">13</u>The image inspection method according to the invention is the first.<u style="single">10</u>In the present invention, it is preferable that the second threshold value is set by subtracting a predetermined value from the first threshold value in the second threshold value setting step, which includes an input receiving step of receiving the input of the first threshold value.</p><p> With such a configuration, when the user wants to detect only blobs having a brightness difference of a predetermined value or more with respect to the first threshold value input in the input reception process, the second threshold value is automatically set, which is convenient. There is sex.</p><p> No.<u style="single">14</u>The image inspection method according to the invention is the first.<u style="single">10</u>In the present invention, it is preferable that the first threshold value is set to a value obtained by adding a predetermined value to the second threshold value in the first threshold value setting step, which includes an input receiving step of receiving the input of the second threshold value.</p><p> With such a configuration, the user inputs the second threshold value in the input reception process, and a blob having a brightness value larger than the input second threshold value is detected, but the user raises the second threshold value by a predetermined value from the second threshold value. It is convenient because the first threshold is automatically set when you want to identify and detect the blob with one threshold.</p><p> In order to achieve the second purpose,<u style="single">15</u>The image inspection method according to the invention is the first.<u style="single">11</u>To the first<u style="single">14</u>In any one of the inventions, a segment setting step of setting a segment of a predetermined size for the multi-valued image acquired in the image acquisition step and a predetermined segment of the segment set in the segment setting step are specified. It may include a segment image generation step of calculating the average brightness value of the pixels in the segment while moving the pixel unit, generating a segment image having the calculated average brightness value, and sending the segment image to the labeling processing step. preferable.</p><p> With such a configuration, a segment image is generated with the average brightness value of all the pixels in the segment calculated while moving a segment of a predetermined size in a predetermined pixel unit as one pixel value, and two threshold values are set for the segment image. By performing the processing used, even if the detection target has a small area and a plurality of detection targets are collectively present in a predetermined area, the plurality of objects can be detected as one blob. , The ability to discriminate blobs can be improved.</p><p> No.<u style="single">16</u>The image inspection method according to the invention is the first.<u style="single">15</u>In the present invention, the predetermined size of the segment and the predetermined pixel unit of movement are received in the input receiving step.<u style="single">Keru</u>Is preferable.</p><p> With such a configuration, the user can freely set the segment size (number of pixels in the X and Y directions) and the amount of movement (number of pixels in the X and Y directions) to detect an object as one blob. It can be adjusted freely.</p><p> No.<u style="single">17</u>The computer program according to the present invention includes an image acquisition process for capturing an image of an inspection target area to acquire a multi-valued image, and a minimum luminance value to be detected in the detection target image.<u style="single">Or the maximum brightness value</u>1st threshold setting process and<u style="single">When the minimum luminance value is set as the first threshold value in the first threshold value setting process,</u>A plurality of pixels having a brightness value larger than the first threshold value are extracted from the multi-valued image acquired by the image acquisition process, and based on the connectivity of the extracted brightness values of the plurality of pixels.<u style="single">, Can be detected</u>Identify a collection of pixels<u style="single">When the maximum brightness value is set as the first threshold value in the first threshold value setting process, a plurality of images having a brightness value smaller than the first threshold value from the multi-valued image acquired in the image acquisition process. Pixels are extracted, and an aggregate of pixels that can be detected is specified based on the connectivity of the brightness values of the extracted plurality of pixels.</u>Labeling process to be performed, the first determination process for determining whether or not there is a request for changing the setting of the first threshold value after the labeling process, and the setting change of the first threshold value by the first determination process. When it is determined that there is a request for the first threshold value, the first threshold value resetting process for resetting the first threshold value, and when the first threshold value resetting process is performed, the first branching process for branching to the labeling process. , The first threshold value for an aggregate of pixels specified by the labeling process.<u style="single">Different from</u>The second threshold setting process for setting the second threshold and<u style="single">In the first threshold value setting process, the minimum luminance value is set as the first threshold value,</u>It was set in the second threshold setting process.<u style="single">When the second threshold value is larger than the first threshold value,</u>An aggregate of the pixels consisting only of brightness values smaller than the second threshold value.<u style="single">When it is deleted from the detection target, the maximum luminance value is set as the first threshold value by the first threshold value setting process, and the second threshold value set by the second threshold value setting process is smaller than the first threshold value, the above. An aggregate of the pixels consisting only of brightness values larger than the second threshold value is detected from the detection target.</u>The deletion process for deleting, the second determination process for determining whether or not there is a request for changing the setting of the second threshold value after the deletion process, and the setting of the second threshold value by the second determination process. When it is determined that there is a request for change, the second threshold value resetting process for resetting the second threshold value and the second branching process for branching to the deletion process when the second threshold value resetting process is performed. And let the computer do<u style="single">It is characterized by that.</u></p><p> With such a configuration, while changing the settings of the first threshold value and / or the second threshold value, the blob consisting only of the luminance values having a large area to be undetected and smaller than the second threshold value from the multi-valued image.<u style="single">Or a blob consisting only of brightness values smaller than the second threshold</u>Is surely removed as noise, and the part with low brightness value in the blob to be detected<u style="single">Or high part</u>Can be detected without dividing the blob to be detected even when is present.</p><p> No.<u style="single">18</u>The computer program according to the invention is the first<u style="single">17</u>In the invention<u style="single">Said</u>A segment setting process for setting a segment of a predetermined size for the multi-valued image acquired in the image acquisition process, and a segment set in the segment setting process while moving the segment in a predetermined pixel unit. The average brightness value of the pixels of the above is calculated, a segment image having the calculated average brightness value is generated, and after performing the segment image generation processing to be the target of the labeling processing and the segment image generation processing, the segment A third determination process for determining whether or not there is a request for changing the size and / or movement pixel unit setting of the size and / or movement, and a request for changing the size and / or movement pixel unit setting change by the third determination process. When it is determined that there is, the segment resetting process for resetting the size and / or the pixel unit of the movement, and the third branch branching to the segment image generation process when the segment resetting process is performed. It is preferable to let the computer perform the processing further.</p><p> With such a configuration, a segment image is generated with the average brightness value of all the pixels in the segment calculated while moving a segment of a desired size in a desired pixel unit as one pixel value, and two threshold values are set for the segment image. By performing the processing used, even if the detection target has a small area and a plurality of detection targets are collectively present in a predetermined area, the plurality of objects can be detected as one blob. , The ability to discriminate blobs can be improved.</p>
<p> According to the present invention, a blob having a large area of a non-detection target is surely removed as noise from a multi-valued image, and the brightness value of the non-detection target to be removed as noise in the blob of the detection target is lower (or higher) than the brightness value. ) Provided is an image inspection device capable of detecting a blob to be detected without dividing it even when a luminance value is present, an image inspection method, and a computer program for executing each processing step of the image inspection method. It becomes possible to do.</p><p> Further, according to the present invention, in addition to the above effects, even if the detection target has a small area and a plurality of detection objects are collectively present in a predetermined area, a plurality of objects are included in one. It can be detected as a blob, and the ability to discriminate blobs can be improved. It should be noted that a plurality of pixels having a brightness value smaller (larger) than the first threshold value are extracted from the multi-valued image acquired by the image acquisition process, and a pixel consisting of only a brightness value larger (smaller) than the set second threshold value is extracted. To delete the aggregate of, multiple pixels having a brightness value smaller (larger) than the first threshold value are extracted from the multi-valued image acquired by the image acquisition process, and the pixel is larger than the set second threshold value ( The same effect can be expected by deleting an aggregate of pixels consisting only of a small) brightness value.</p>
Hereinafter, embodiments of the present invention will be described with reference to the drawings. In the drawings referred to in the description of each embodiment, elements having the same or similar configuration or function are designated by the same or similar reference numerals, and detailed description thereof will be omitted.
(Embodiment 1) FIG. 1 is a block diagram showing a configuration example of an image inspection device according to a first embodiment of the present invention. In FIG. 1, the image inspection device 1A according to the first embodiment includes an image pickup means 2, an image processing unit 3A, a storage means 4, an input reception means 5A, and an output means 6.
The image pickup means 2 functions as, for example, a two-dimensional CCD camera, for example, captures a work (inspection target area) on a film, acquires a multi-valued image, and outputs it to the image processing unit 3A.
The image processing unit 3A includes a first threshold value setting means 31, a labeling processing means 32, a second threshold value setting means 33, and a deletion means 34. Further, the image processing unit 3A is composed of a CPU, ROM, RAM, an external I / F, etc., and performs processing operations of the first threshold value setting means 31, the labeling processing means 32, the second threshold value setting means 33, and the deletion means 34. Control.
Prior to selecting the threshold value described later using the first threshold value setting means 31, the user is informed by a graphical user interface (not shown) that "Mode 1: Luminance of an undetected object to be removed as noise in the blob to be detected". If there is a possibility that there is a brightness value lower than the value (the case where the inside of the blob is composed of something with a high brightness value as a whole compared to the background) "or" Mode 2: Noise in the target blob There is a possibility that there is a brightness value higher than the brightness value of the undetected object that you want to remove as (a case where the inside of the blob is composed of things with a lower brightness value as a whole compared to the background). Let them choose whether to adopt the mode that satisfies the above conditions.
The first threshold value setting means 31 receives the first threshold value received from the user by the input receiving means 5A, and sets the first threshold value for the labeling processing means 32. As the first threshold value, the user selects the minimum luminance value Lmin or the maximum luminance value Lmax to be detected as the user from the luminance values existing in the image to be detected.
More specifically, when the above mode 1 is selected, the input receiving means 5A accepts the input of the minimum luminance value Lmin to be detected, and when the above mode 2 is selected, the input receiving means 5A accepts the input. The function is automatically switched to accept the input of the maximum brightness value Lmax to be detected.
When a blob with a brightness value higher than the first threshold value is detected, that is, when mode 1 is selected, the set first threshold value is represented by TH1 (Lmin), and a blob with a brightness value lower than the first threshold value is expressed. When is detected, that is, when mode 2 is selected, the set first threshold value is expressed as TH1 (Lmax).
As a method of selecting mode 1 or mode 2, it is also possible to set "greater than" or "less than" at the same time when setting the first threshold value described above.
The labeling processing means 32 extracts a plurality of pixels having a brightness value larger than the first threshold value TH1 (Lmin) or smaller than TH1 (Lmax) from the multi-valued image acquired by the imaging means 2, and the extracted plurality of pixels. A labeling process for specifying an aggregate of pixels (hereinafter referred to as a blob) is performed based on the connectivity of the brightness values of the pixels, and a labeling processed image is output.
The second threshold value setting means 33 receives the second threshold value received from the user by the input receiving means 5A, and sets the second threshold value TH2 (Lmin) or TH2 (Lmax) for the deleting means 34. More specifically, in the above-mentioned mode 1, the second threshold value TH2 (Lmin) is set, and in the mode 2, TH2 (Lmax) is set. Here, the second threshold value TH2 (Lmin) is larger than the first threshold value TH1 (Lmin), and the second threshold value TH2 (Lmax) is smaller than the first threshold value TH1 (Lmax).
The deleting means 34 removes blobs consisting only of luminance values equal to or less than the second threshold value TH2 (Lmin) or greater than TH2 (Lmax) set by the second threshold value setting means 33 from all the blobs specified by the labeling processing means 32. Delete and output the noise processed image.
The storage means 4 functions as an image memory, and stores a multi-valued image captured by the imaging means 2, a labeling processed image obtained by the labeling processing means 32, and a noise processed image obtained by the deleting means 34 at any time. The input receiving means 5A accepts the input of the first threshold value TH1 (Lmin) or TH1 (Lmax) and the second threshold value TH2 (Lmin) or TH2 (Lmax) from the user. The output means 6 functions as an image display device, and displays a multi-valued image, a labeling processed image, or a noise processed image on the screen.
FIG. 2 is a flowchart showing each processing step of the image inspection method according to the present invention used in the image inspection apparatus 1A according to the first embodiment. Each processing step of the image inspection method according to the present invention is executed according to the computer program according to the present invention stored inside the image processing unit 3A.
In FIG. 2, first, the image processing unit 3A acquires a multi-valued image of the inspection target area by imaging in the image acquisition process (step S201). Next, the image processing unit 3A accepts the user input of the first threshold value in the input reception process, and sets the first threshold value input by the user for the labeling process in the first threshold value setting process (step S202). ).
Next, the image processing unit 3A performs labeling processing according to the first threshold value set by the first threshold value setting processing, and outputs the resulting labeling processed image (step S203). The labeling processed image is displayed on the screen, and the user confirms the displayed image and determines whether or not to change the first threshold value. This judgment by the user is made based on whether or not all the blobs (noise) to be detected and the blobs (defects) to be detected are displayed on the screen.
Next, the image processing unit 3A determines whether or not the user has changed the input of the first threshold value based on the result of the input reception process (whether or not there is a request to change the setting of the first threshold value) (step S204). 1 When there is an input change of the threshold value (step S204: YES), the first threshold value is reset in the first threshold value reset processing (step S205), and the processing is returned to step S203.
FIG. 3 is a diagram showing an example of a display screen of the labeling processed image. On the screen of FIG. 3, four blobs B1 and B2 to be detected and blobs B3 and B4 to be detected are displayed as labeling processed images. In this example, the first threshold TH1 (Lmin) is used for the labeling process. The blob B1 to be undetected is composed of pixels having a large area and a uniform low luminance value. The blob B2 to be undetected is composed of pixels having a small area and a high luminance value in a part. The blobs B3 and B4 to be detected are composed of pixels having a plurality of low-luminance values and a plurality of high-luminance values. In the blob, the shaded portion indicates a pixel having a high luminance value, and the portion not shaded indicates a pixel having a low luminance value.
As shown in FIG. 3, when all the blobs B1 to B4 are detected and the image processing unit 3A determines that the input of the first threshold value is not changed by the user (step S204: NO), the input acceptance process is performed. The user input of the second threshold value is received, and the second threshold value input by the input reception process is set for the deletion process in the second threshold value setting process (step S206).
Next, the image processing unit 3A performs the deletion process according to the second threshold value set by the second threshold value setting process, and outputs the noise-processed image obtained by the deletion process (step S207). The noise-processed image is displayed on the screen, and the user checks the displayed image to determine whether or not to change the second threshold value. This user's judgment is based on whether or not only the blob (defect) to be detected is displayed on the screen.
Next, the image processing unit 3A determines whether or not the user has changed the input of the second threshold value based on the result of the input reception process (whether or not there is a request to change the setting of the second threshold value) (step S208). 2 When there is an input change of the threshold value (step S208: YES), the second threshold value is reset in the second threshold value reset processing (step S209), and the processing is returned to step S207.
FIG. 4 is a diagram showing an example of a display screen of a noise processed image. On the screen of FIG. 4, blobs B2 to be undetected and blobs B3 and B4 to be detected are displayed as noise-processed images. Since the non-detection target blob B1 displayed in FIG. 3 consists only of a luminance value smaller than the second threshold value TH2 (Lmin), it is deleted in FIG. 4 by the deletion process. The blob B2 to be undetected remains because it has a high luminance value in part, but since it has a small area, it is excluded as noise by setting a lower limit of the area using, for example, an area filter. The blobs B3 and B4 to be detected having a plurality of low-luminance values partially are detected without being divided.
As shown in FIG. 4, the non-detection target blob B1 having a large area is deleted as noise, and the non-detection target blob B2 having a small area can be excluded as noise by processing using an area filter. , The blobs B3 and B4 to be detected are stably detected, and when the image processing unit 3A determines that the input change of the second threshold value is not changed by the user (step S208: NO), the process is terminated.
As described above, according to the first embodiment of the present invention, the non-detection target and the detection target blob having a brightness value larger than the first threshold value TH1 (Lmin) or smaller than TH1 (Lmax) are obtained by the labeling process. By identifying and deleting, blobs with a large area to be undetected, consisting only of luminance values smaller than the second threshold TH2 (Lmin) or larger than TH2 (Lmax), were extracted from all blobs identified by the labeling process. By deleting it as noise, even if a portion having a low brightness value exists in the blob to be detected, the blob to be detected can be detected without being divided.
(Embodiment 2) FIG. 5 is a block diagram showing a configuration example of the image inspection device according to the second embodiment of the present invention. In FIG. 5, the image inspection device 1B according to the second embodiment includes an image pickup means 2, an image processing unit 3B, a storage means 4, an input reception means 5B, and an output means 6.
The difference between the second embodiment and the first embodiment is that the segment setting means 35 and the segment image generation means 36 are added to the image processing unit 3A of the first embodiment to form the image processing unit 3B. The input receiving means 5B is at a point where it receives inputs of the segment size and the amount of movement in addition to the first threshold and the second threshold. Hereinafter, this difference will be mainly described.
The segment setting means 35 inputs a segment of a size desired by the user (the number of pixels in the X direction and the number of pixels in the Y direction) input from the input receiving means 5B with respect to the multi-valued image acquired by the imaging means 2. , Set for the segment image generation means 36.
The segment image generation means 36 moves the segment of the size set by the segment setting means 35 in pixel units (movement amount: the number of pixels in the X direction and the number of pixels in the Y direction) desired by the user, while moving the pixels in the segment. The average brightness value of is calculated, and a segment image having the calculated average brightness value is generated. Here, since the segment image is output to the image display device as the output means 6 and displayed on the screen of the image display device, the user adjusts the size and movement amount of the segment while checking the segment image. Can be done.
FIG. 6 is a flowchart showing each processing step of the image inspection method according to the present invention used in the image inspection apparatus 1B according to the second embodiment. Each processing step of the image inspection method according to the present invention is executed according to the computer program according to the present invention stored inside the image processing unit 3B.
In FIG. 6, first, the image processing unit 3B acquires a multi-valued image of the inspection target area by imaging in the image acquisition process (step S201). Next, the image processing unit 3B accepts the user's input of the segment size and movement amount in the input reception processing, and converts the input segment size and movement amount into the segment image generation processing in the segment setting processing. Set for (step S601).
Next, the image processing unit 3B calculates the average luminance value of the pixels in the segment while moving the segment of the set size with the set movement amount in the segment image generation processing, and the calculated average. Generate a segment image with a brightness value (step S602).
Next, the image processing unit 3B determines whether or not the user changes the input of the segment size and / or the movement amount based on the result of the input reception processing (whether or not there is a request to change the setting of the segment size and / or the movement amount). If there is an input change (step S603: YES), the segment size and / or movement amount is reset in the segment reset process (step S604), and the process is changed to step S602. return.
On the other hand, when the image processing unit 3B determines that the input of the segment size or movement amount is not changed by the user (step S603: NO), the input acceptance process accepts the user input of the first threshold value and sets the first threshold value. In the process, the input first threshold value is set for the labeling process (step S202). Since the subsequent processing is the same as that of FIG. 2 referred to in the description of the first embodiment, the description thereof will be omitted.
As described above, according to the second embodiment of the present invention, the average brightness value of all the pixels in the segment calculated while moving the segment of the size desired by the user in the desired pixel unit (movement amount) is 1. When a segment image is generated as a pixel value and processing is performed on the segment image using two threshold values, so that the detection target has a small area and a plurality of detection objects are collectively present in a predetermined area. In addition, a plurality of objects can be detected as one blob, and the blob discrimination ability can be improved.
FIG. 7 is a diagram showing an example of a display screen of the original multi-valued image before the segment image is generated, and FIG. 8 is a diagram showing an example of the display screen of the segment image. In FIG. 7, even when the detection target has a small area and a plurality of detection objects are collectively present in a predetermined region R, as shown in FIG. 8, a plurality of detection objects can be generated by generating a segment image. The object can be detected as one blob B5.
In the first and second embodiments of the present invention, an example in which both the first threshold value and the second threshold value are input by the user has been described, but the present invention is not limited to such a configuration, and one of the threshold values is set by the user. Is input, and the other threshold value may be set as a value obtained by adding or subtracting a predetermined value.
For example, the user inputs only the first threshold value TH1 (Lmin), and the second threshold value TH2 (Lmin) is set by the second threshold value setting means 33 as a value obtained by adding a predetermined value to the first threshold value TH1 (Lmin). To. Alternatively, the user inputs only the first threshold value TH1 (Lmax), and the second threshold value TH2 (Lmax) is set by the second threshold value setting means 33 as a value obtained by subtracting a predetermined value from the first threshold value TH1 (Lmax). To. As a result, when the user wants to detect only blobs having a brightness difference of a predetermined value or more with respect to the freely input first threshold value, the second threshold value is automatically set, which is convenient.
Further, the user inputs only the second threshold value TH2 (Lmin), and the first threshold value TH1 (Lmin) is set by the first threshold value setting means 31 as a value obtained by subtracting a predetermined value from the second threshold value TH2 (Lmin). To. Alternatively, the user inputs only the second threshold value TH2 (Lmax), and the first threshold value TH1 (Lmax) is set by the first threshold value setting means 31 as a value obtained by adding a predetermined value to the second threshold value TH2 (Lmax). To. As a result, a blob having a brightness value smaller than the second threshold value TH2 (Lmin) or larger than TH2 (Lmax) input by the user is detected, but the user lowers the blob by a predetermined value from the second threshold value TH2 (Lmin). When you want to identify and detect a blob with the first threshold TH1 (Lmin) or the first threshold TH1 (Lmax) that is higher than the second threshold TH2 (Lmax) by a predetermined value, the first threshold is automatically set. It is convenient because it is set.
In the first embodiment of the present invention, the input receiving means 5A and the output means 6 are described as different configurations, and in the second embodiment of the present invention, the input receiving means 5B and the output means 6 are described as different configurations. However, the present invention is not limited to such a configuration, and the display area of the image display device as the output means 6 may be divided and the input receiving means 5A and 5B may be provided as a dialog box adjacent to the image display area. Good. As a result, the image display screen is updated every time the user changes parameters such as the first threshold value, the second threshold value, the segment size and movement amount, and the upper and lower limits of the blob area to be detected on the dialog box. Therefore, the user can easily adjust the necessary parameters while checking the updated display image.
The image inspection device according to the present invention has an advantage that noise of a non-detection target can be reliably removed and defects such as scratches and stains of the detection target can be stably detected, and as an inspection device using an image of defects. It is applied to various uses.
<figref num="1">A block diagram showing a configuration example of an image inspection device according to a first embodiment of the present invention.</figref><figref num="2">A flowchart showing each processing step in the image inspection method according to the first embodiment of the present invention.</figref><figref num="3">The figure which shows an example of the display screen of the labeling processed image by Embodiment 1 of this invention.</figref><figref num="4">The figure which shows an example of the display screen of the noise processing image by Embodiment 1 of this invention.</figref><figref num="5">A block diagram showing a configuration example of an image inspection device according to a second embodiment of the present invention.</figref><figref num="6">A flowchart showing each processing step in the image inspection method according to the second embodiment of the present invention.</figref><figref num="7">The figure which shows an example of the display screen of the original multi-valued image before generating the segment image by Embodiment 2 of this invention.</figref><figref num="8">The figure which shows an example of the display screen of the segment image by Embodiment 2 of this invention.</figref>
Code description
1A, 1B image inspection equipment 2 Imaging means 3A, 3B image processing unit 4 Memories 5A, 5B Input reception means 6 Output means 31 First threshold setting means 32 Labeling processing means 33 Second threshold setting means 34 Deletion means 35 Segment setting means 36 Segment image generation means
Every citation, both ways
| Document | Relation | Office |
|---|---|---|
| WO03054530A1 | Cites | World Intellectual Property Organization (WIPO) |
| JP09189528A | Cites | Japan |
| JP2006041352A | Cites | Japan |
| JP2006078380A | Cites | Japan |
| JP10269352A | Cites | Japan |
| JP2003222597A | Cites | Japan |
| JP2006259788A | Cites | Japan |
12 members in 4 offices
Priority claims2
| Document | Office | Kind | Date |
|---|---|---|---|
| 2008029514 | Japan | A | |
| JP20080029514 | – | – | – |
Members12
| Document | Office | Kind | |
|---|---|---|---|
| US2009202172A1 | United States of America | A1 | |
| WO2009098943A1 | World Intellectual Property Organization (WIPO) | A1 | |
| JP2009185964A | Japan | A | |
| JP2009186434A | Japan | A | |
| EP2246587A1 | European Patent Office (EPO) | A1 | |
| US2011001296A1 | United States of America | A1 | |
| US8014628B2 | United States of America | B2 | |
| JP5085363B2 | Japan | B2 | |
| JP5086830B2This record | Japan | B2 | |
| US8701845B2 | United States of America | B2 | |
| EP2246587A4 | European Patent Office (EPO) | A4 | |
| EP2246587B1 | European Patent Office (EPO) | B1 |
18 legal events, as the office reported them to INPADOC
Over the term
Point at a mark for the eventEvents
| Event | Code | |
|---|---|---|
| Cancellation because of no payment of annual feesLAPS | LAPS | |
| Receipt of annual feesJAPANESE INTERMEDIATE CODE: R250R250 | R250 | |
| Receipt of annual feesJAPANESE INTERMEDIATE CODE: R250R250 | R250 | |
| Receipt of annual feesJAPANESE INTERMEDIATE CODE: R250R250 | R250 | |
| Receipt of annual feesJAPANESE INTERMEDIATE CODE: R250R250 | R250 | |
| Receipt of annual feesJAPANESE INTERMEDIATE CODE: R250R250 | R250 | |
| Renewal fee payment (event date is renewal date of database)FPAY | FPAY | |
| Certificate of patent or registration of utility modelJAPANESE INTERMEDIATE CODE: R150R150 | R150 | |
| Certificate of patent or registration of utility modelJAPANESE INTERMEDIATE CODE: R150R150 | R150 | |
| First payment of annual fees (during grant procedure)JAPANESE INTERMEDIATE CODE: A61A61 | A61 | |
| Written decision to grant a patent or to grant a registration (utility model)JAPANESE INTERMEDIATE CODE: A01A01 | A01 | |
| Written decision to grant a patent or to grant a registration (utility model)JAPANESE INTERMEDIATE CODE: A01A01 | A01 | |
| Decision of grant or rejection writtenTRDD | TRDD | |
| Request for written amendment filedJAPANESE INTERMEDIATE CODE: A523A521 | A521 | |
| Notification of acceptance of power of attorneyJAPANESE INTERMEDIATE CODE: A7422RD02 | RD02 | |
| Notification of reasons for refusalJAPANESE INTERMEDIATE CODE: A131A131 | A131 | |
| Report on retrievalJAPANESE INTERMEDIATE CODE: A971007A977 | A977 | |
| Written request for application examinationJAPANESE INTERMEDIATE CODE: A621A621 | A621 |
Numbers
- Publication
- 5086830
- Publication, DOCDB
- 5086830
- Publication, EPODOC
- JP5086830B
- Application
- 29514
- Application, DOCDB
- 2008029514
- Application, EPODOC
- JP20080029514
Titles2
- Japanese
- 画像検査装置、画像検査方法、及びコンピュータプログラム
- English
- Image inspection equipment, image inspection methods, and computer programs
Classification
- CPC, 1
- G06V10/273
- IPC, 4
- G01N21 88
- G06T1 00
- G06T5 00
- G06T7 60