Image processor and method for image processing

[Industrial Application Field] The present invention reads a manuscript image on which input characters and images are printed, recognizes the read character image as characters, and converts the recognized characters into a predetermined language. It relates to an image processing device and an image processing method for translating and outputting an image.

[0002] Conventional Techniques Conventionally, when creating a business card displayed in English based on a business card manuscript printed in Japanese by using, for example, this type of image processing device, an English version is used. I created a new one and printed it.

[0003] Further, when creating a business card in which one side is in Japanese and the other side is in English based on the manuscript of the business card printed in Japanese on one side, the Japanese version and the English version are used. I created both of them from the beginning and printed them with a double-sided printing device.

[0004] [Problems to be Solved by the Invention] As described above, in the above-mentioned conventional example, although the Japanese business card information as the manuscript is created, the business card version information for English is completely newly provided. There was a problem that I had to create it.

[0005] The present invention has been made to solve the above problems, and an object of the present invention is to separate an image data and a document image data from the original manuscript image data in which the manuscript image has been input, and to separate the image data and the document image data. Character-recognized characters are translated into other languages from the document image data, and further, print data laid out based on the area-separated document data area information and the second character data is generated and translated. By allocating characters and input manuscript images to each side of the recording medium and printing on both sides, a simple manuscript image input operation can translate a character image based on one language into another language for layout printing, or It is an object of the present invention to provide an image processing apparatus and an image processing method capable of performing double-sided printing by distributing the data to each side of the same recording medium.

[Means for Solving the Problems] The first invention according to the present invention is a manuscript input means for inputting an image of a manuscript including a first character and an image based on a first language, and the manuscript input means. A separation means that analyzes the manuscript image data input from the image and separates the area into a document data area and an image data area, and a character image is cut out from the document data area separated by the separation means to obtain the first character. A recognition means for recognizing, a translation means for translating the character data corresponding to the first character recognized by the recognition means into the second character data based on the second language, and a document region-separated by the separation means. A data generation means that generates print data laid out based on the data area information and the second character data, and a second character data and the manuscript image data based on the print data generated by the data generation means. It is characterized by having a printing means for allocating the data to each side of the recording medium and printing on both sides.

[0007] The second invention according to the present invention is a manuscript input step of inputting an image of a manuscript including a first character and an image based on a first language from a manuscript input means, and the manuscript image data of the image input. A separation step of analyzing and separating the area into a document data area and an image data area, a recognition step of cutting out a character image from the separated document data area and recognizing the first character, and the recognized first The translation process of translating the character data corresponding to the characters in the second language into the second character data based on the second language, the document data area information separated by the area, and the print data laid out based on the second character data. It is characterized by having a data generation step of generating the data, and a printing step of allocating the second character data and the original image data to each side of the recording medium and printing on both sides based on the generated print data. To do.

[Example] [First Example] In the first embodiment of the present invention, an image and a character in a manuscript image are recognized, and the recognized character is translated into a predetermined language. For example, a case where each is printed on the front and back as a business card is taken as an example.

[0019] Here, a case where the language input from the manuscript is Japanese and the language to be translated and printed is English will be described.

FIG. 1 is a block diagram illustrating a configuration of an image processing apparatus showing a first embodiment of the present invention.

[0021] In the figure, 1 is an input unit for a document, and a flatbed scanner or the like corresponds to this. From here, the Japanese business card that will be the manuscript is input. The manuscript image data input by the input unit 1 is sent to the recognition unit 9, which will be described later. The recognition unit 9 has a function of receiving the manuscript image data sent from the input unit 1, separating the area where characters and pictures are drawn, and further recognizing the contents of the character image drawn there. have.

[0022] The layout information such as the position and size of the character area separated by the recognition unit 9 and the recognized character content are sent to the processing unit 2 described later. The processing unit 2 comprehensively controls each unit to be described later including the input unit 1 and the recognition unit 9, and performs processing such as creating an output plate here.

[0023] 3 is a storage unit, which is composed of a hard disk or the like, and temporarily stores data sent from the recognition unit 9 to the processing unit 2, or processing data required by the processing unit 2 in the translation unit 5, which will be described later. Etc. are stored.

[0024] Reference numeral 4 denotes a display unit, which corresponds to a monitor or the like. Here, the input status from the input unit 1 is displayed, and the layout before output is displayed for confirmation. Reference numeral 5 denotes a translation unit, which translates the Japanese recognized by the recognition unit 9 into a predetermined language, for example, English. Reference numeral 6 denotes a printing unit, and in this embodiment, characters recognized as business cards and translated characters of these characters are printed on the front and back surfaces. The printing unit 6 has a function of printing characters and images with a set of points, such as an inkjet printer and a laser printer. Further, a storage unit 7 is built in the printing unit 6, and is configured to hold print data used by the printing unit 6.

[0026] In the image processing apparatus configured as described above, specifically, a manuscript input means (input unit 1) for inputting an image of a manuscript including a first character and an image based on a first language, and this Separation means (by the separation process of the recognition unit 9) that analyzes the manuscript image data input from the manuscript input means and separates the area into the document data area and the image data area, and the document data separated by the separation means. The recognition means (by the recognition process of the recognition unit 9) that cuts out the character image from the area and recognizes the first character, and the character data corresponding to the first character recognized by this recognition means are based on the second language. A translation means for translating into the second character data (translation unit 5), and a data generation means for generating document data area information separated by the separation means and print data laid out based on the second character data. It has (processing unit 2) and printing means (printing unit 6) for printing second character data on a recording medium based on the print data generated by the data generating means, and the original is input by the recognition unit 9. When the manuscript image data input as an image from the means is analyzed and the area is separated into a document data area and an image data area, a character image is cut out from the separated document data area to recognize the first character. The translation unit 3 translates the character data corresponding to the recognized first character into the second character data based on the second language, and the document data area information separated by the processing unit 2 and the above. When the print data laid out based on the second character data is generated, the printing unit 6 prints the second character data on the recording medium based on the generated print data, and prints the document manuscript image. It is possible to print the character information translated into another language with respect to the character information based on one language from the input operation in the layout corresponding to the manuscript.

Next, a schematic process of image processing according to the image processing apparatus according to the present invention will be described with reference to the flowchart shown in FIG.

[0028] FIG. 2 is a flowchart showing an example of a schematic processing procedure of the first image processing according to the image processing apparatus according to the present invention. Note that (1) to (5) indicate each step.

[0029] First, when an image of a Japanese business card to be a manuscript is input from an input unit 1 such as a flatbed scanner (1), the manuscript image data input by the input unit 1 is sent to the recognition unit 9. Be done. Next, the recognition unit 9 executes a recognition processing routine described later (2). The processing unit 2 reads only the Japanese data out of the Japanese data, the image information, and the layout information recognized in the step (2) and stored in the storage unit 3, and sends the data to the translation unit 5. The translation unit 5 has a translation function from Japanese to English, translates the input Japanese data into English, and executes the English translation process of returning it to the processing unit 2 again (3).

[0030] For example, when the name "Ichiro Yamada" is sent, "Ichirou Yamada" is returned (since "Ichiro Yamada" is a unique business card, it was simply converted to Roman alphabet, but for example, "telephone". Is converted to "Telephone" or the abbreviated "Tel."). As for the method of translating from Japanese to English, various methods have been proposed so far, so detailed description thereof will be omitted here. The English data sent to the processing unit 2 is sent to the storage unit 3 and temporarily stored.

Next, at the stage when step (3) is completed, four types of information, Japanese data, English data, image information, and layout information, are stored in the storage unit 3. Of these, print data for English business cards is created by using English data, image information, and layout information (4). Specifically, the English data is such that the character code is a set of pixels representing a font of the specified size at the position specified in the layout information and at the resolution corresponding to the printing unit 6. Expanded on memory. At this time, depending on the difference in the number of characters between Japanese and English, English characters may not fit in the specified layout. In this case, reduce the character size or do not overlap with other areas. It is necessary to perform processing such as expanding the size of the layout.

[0032] Further, the image information is arranged as an image as it is at the position of the layout information.

The English print data thus created is as shown in FIG. 3 (f), which will be described later, and is sent to the storage unit 7 inside the print unit 6.

Next, the printing unit 6 prints English on the printing paper for business cards using the English printing data stored in the storage unit 7 (5), and ends the process.

[0036] In the image processing method configured as described above, specifically, a manuscript input in which a manuscript containing a first character and an image based on a first language is input as an image from a manuscript input means (input unit 1). A step (step (1) in FIG. 2), a separation step (step (2) in FIG. 2) that analyzes the manuscript image data input to the image and separates the area into a document data area and an image data area, and the same. A recognition step (step (2) in FIG. 2) of cutting out a character image from the separated document data area and recognizing the first character, and a second character data corresponding to the recognized first character. A translation process for translating into the second character data based on the language (step (3) in FIG. 2), and generation of the area-separated document data area information and print data laid out based on the second character data. The data generation step (step (4) in FIG. 2) and the printing step (step (5) in FIG. 2) for printing the second character data on the recording medium based on the generated print data are programmed. The processing unit 2 executes the process based on the above, and is programmable to print the character information translated into another language for the character information based on one language from the operation of inputting the document manuscript image in the layout corresponding to the manuscript. Make it feasible.

[0037] Hereinafter, the recognition processing routine shown in FIG. 2 will be described in detail with reference to FIGS. 3 and 4.

[0038] FIG. 3 is a diagram illustrating a document image recognition processing state in the image processing apparatus according to the present invention.

[0039] FIG. 4 is a flowchart showing an example of a detailed procedure of the recognition processing routine shown in FIG. Note that (1) to (8) indicate each step.

[0040] It is assumed that the recognition unit 9 receives the manuscript image data as shown in FIG. 3 (a) read as an image from the input unit 1.

[0041] First, the area of the original image data is separated (1). In this embodiment, the area separation is a process of cutting out a single image area or character area, and areas 11 to 16 as shown in gray in FIG. 3 (b) are required. This area is obtained by grouping images different from the background color of the original image into a group of rectangular areas.

Next, one of the areas cut out in step (1) is selected (2). Then, it is determined whether the selected area is an image area or a character area (3). This has features such as various colors are used for images, tonality data, and it does not matter if there is a filled area, and for characters, it may be a single color. Judgment is made by utilizing the fact that there are many features such as a combination of lines with a certain width.

[0043] If the selected area is determined to be a character area in the determination in step (3), the process proceeds to step (4), and if it is determined to be an image area, the process proceeds to (7).

In the example of FIG. 3B, areas 11 to 15 are determined to be character areas and proceed to step (4), and area 16 is determined to be an image area and proceed to step (7). It will be.

[0045] In this way, when the character area is determined in step (3), the small area separation process is performed (4). In this embodiment, as shown in (d) of FIG. 3, the small area separation process is as shown in (e) of FIG. 3 by cutting out one character at a time from the area 12 called "Ichiro Yamada". It is a process to create various areas 17 to 20. This is achieved by performing the region separation process of step (1) shown in FIG. 4 at a finer level for one region (for example, region 12).

Next, character recognition processing is performed (5). This is a process of determining what kind of character each of the areas 17 to 20 separated into each character is in step (4). By this character recognition process, each character image is converted into a character code.

[0047] This has a dictionary in which the characteristic elements of every character and the code of the character are paired, and by comparing the characteristic elements of the character to be recognized, one of the characters is specified and the character is identified. It is realized by returning the character code.

[0048] Next, a process of storing the character layout information and the character code information is executed (6). For example, in the case of the character area of "Ichiro Yamada" in area 12 of (b) in FIG. 3, the coordinate values (x12, y12) at the upper left of the area, the width w12 of the area, and the height h12 of the area are , Stored as layout information. Then, the character code recognized in step (5) is stored in the same manner. The storage process is executed by being sent from the recognition unit 9 to the storage unit 3 via the processing unit 2.

On the other hand, if it is determined that the image is an image in step (3), a process of storing the layout information of the image and the image data itself is executed (7). Here, for example, the logo area 16 shown in FIG. 3 (c) has the upper left coordinate values (x16, y16) of the area, the area width w16, and the area as shown in FIG. 3 (b). Height h16 is stored as layout information. Then, the image data itself of the area 16 is also stored in the same manner. The storage process is executed by being sent from the recognition unit 9 to the storage unit 3 via the processing unit 2 as in the case of the above step (6).

[0050] Next, it is confirmed whether or not the processing has been completed for all the cut out areas (8), and if it has not been completed yet, the process returns to step (2), and the processing for the next area is started, and all of them are processed. When the processing of the area of is completed, the processing is terminated.

[0051] FIG. 5 is a flowchart showing an example of another detailed procedure of the recognition processing routine shown in FIG. Note that (1), (2), (4) to (8) correspond to the same processing steps as in FIG. 4, and (9) shows the steps peculiar to this embodiment. That is, since this recognition processing routine has the same processing parts as the contents of the recognition processing routine shown in FIG. 4, the parts having the same contents are given the same step numbers and the explanations are omitted, and only the different parts are explained. I will decide.

[0052] In the flowchart of FIG. 4, after step (2), a process of determining whether the area is an image area or a character area is incorporated, but in the flowchart of FIG. 5, this is omitted. Continue to step (4).

Therefore, even if it is an image, the processes of steps (4) and (5) are executed on the premise that it is a character. In the case of an image, as a matter of course, the character recognition in step (5) cannot be performed. Therefore, if it is determined after step (5) whether the character recognition is successful or unsuccessful, if it is successful, the character area is displayed. If it fails, it means that it is an image area. Therefore, in this recognition process, in step (9), it is determined whether the character recognition is successful or unsuccessful, and if it is determined to be successful, the process proceeds to step (6), and if it is determined that the character recognition has failed. Is processed to proceed to step (7). This eliminates the need for prior determination of characters and images, and simplifies processing.

[0054] According to the above procedure, it is possible to automatically create a business card written in English simply by inputting a Japanese business card as a manuscript. This eliminates the need to input English, which has the advantage of significantly reducing work time. [Second Example] In the second example, using a business card written in Japanese as the manuscript as in the first example, a double-sided printed business card written in Japanese on one side and written in English on the other side is created. Is an example of.

[0055] Hereinafter, the device configuration and the flowchart will be described, but since most of the device configurations and processing contents are the same as those in the first embodiment, the following description will explain only the different parts, and the parts having the same contents will be described. The same numbers as those in the first embodiment are assigned, and the description thereof will be omitted.

[0056] FIG. 6 is a block diagram illustrating a configuration of an image processing apparatus showing a second embodiment of the present invention, and the same components as those in FIG. 1 are designated by the same reference numerals.

[0057] In the second embodiment, the image data input by the input unit 61 is sent to the recognition unit 9 and at the same time to the processing unit 2. Further, the printing unit 62 is a printing unit having a double-sided printing function, and internally has a storage unit 7 for printing data on one side and a storage unit 8 for printing data on the opposite side.

[0059] In the image processing apparatus configured as described above, specifically, a manuscript input means (input unit 61) for inputting an image of a manuscript including a first character and an image based on a first language, and the manuscript input unit 61. Separation means (by the separation process of the recognition unit 9) that analyzes the manuscript image data input from the manuscript input means and separates the area into the document data area and the image data area, and the document data separated by the separation means. The recognition means (by the recognition process of the recognition unit 9) that cuts out the character image from the area and recognizes the first character, and the character data corresponding to the first character recognized by this recognition means are based on the second language. A translation means for translating into the second character data (translation unit 5), and a data generation means for generating document data area information separated by the separation means and print data laid out based on the second character data. (Processing unit 2) and a printing means (printing) that distributes the second character data or the original image data to each one side of the recording medium and prints on both sides based on the print data generated by the data generation means. When the original image data input from the input unit 61 by the recognition unit 9 is analyzed and the area is separated into a document data area and an image data area, the separated document data area is obtained. The character image was cut out from the character image, the first character was recognized, the character data corresponding to the recognized first character was translated into the second character data based on the second language, and the area was separated. When the print data laid out by the processing unit 2 is generated based on the document data area information and the second character data, the print unit 62 stores the print data in the recording medium 7 and 8 based on the generated print data. The second character data or the manuscript image data stored in the data is distributed to each side of the recording medium and printed on both sides, and the text information based on one language laid out from the operation of inputting the document manuscript image is obtained from the other. It is possible to distribute the text information translated into the above languages and the original document manuscript image into one side of the same recording medium in a layout corresponding to the manuscript and print on both sides.

[0061] Further, the printing means can print the original image data corresponding to the image data area and layout print both the characters and the image in the original image. This embodiment can also be applied to the printing unit 6 of the first embodiment.

[0062] FIG. 7 is a flowchart showing an example of a schematic processing procedure of the second image processing according to the image processing apparatus according to the present invention. Note that (1) to (5) indicate each step. Further, since steps (2) and (3) in the step are the same processes as those in the first embodiment, the description thereof will be omitted, and the steps (1), (4) and (5) having different contents will be described. It will be described in detail.

[0063] First, when a Japanese business card to be a manuscript is input from an input unit 61 such as a flatbed scanner (1), the manuscript image data input by the input unit 61 is input to the recognition unit 9 and It is sent to the processing unit 2. Next, the original image data sent to the recognition unit 9 is subjected to recognition processing (2), and the original image data sent to the processing unit 2 is temporarily stored in the storage unit 3 (3).

Next, at the stage when step (3) is completed, Japanese data, English data, image information, layout information, and manuscript image data input from the input unit 61 in step (1) are stored in the storage unit 3. Has been accumulated. Of these, the English print data is created in the same manner as in the first embodiment and is sent to the storage unit 8 inside the print unit 62. Further, since the original image data itself can be used as the Japanese print data, this is sent to the storage unit 7 inside the print unit 62 to create the print data (4).

Next, Japanese is printed on one side of the recording material using the Japanese print data stored in the storage unit 7, and the English print data stored in the storage unit 8 is used on the other side. Print in English (5) and finish the process.

[0066] As described above, in the second embodiment, it is possible to easily create a business card in which Japanese and English are printed on both sides.

[0067] In step (4) shown in FIG. 7, the Japanese print data was sent to the storage unit 7 using the original image data input from the input unit 61 as it is, but in step (4). Create Japanese print data using the Japanese data, image information, and layout information stored in the storage unit 3 in the same way as when creating the English print data in step 3, and send this to the storage unit 7. A method of printing in Japanese is also possible. If this method is used, Japanese printing can be performed without image deterioration caused by input from the input unit 62, so that higher quality printing can be performed.

[0069] In the image processing method configured as described above, specifically, a manuscript input in which a manuscript containing a first character and an image based on a first language is input as an image from a manuscript input means (input unit 61). A step (step (1) in FIG. 7), a separation step (step (2) in FIG. 7) that analyzes the manuscript image data in which the image is input and separates the area into a document data area and an image data area, and the same. A recognition step (step (2) in FIG. 7) of cutting out a character image from the separated document data area and recognizing the first character, and a second character data corresponding to the recognized first character are used. A translation process for translating into a second character data based on the language (step (3) in FIG. 7), a document data area information separated from the area, and print data laid out based on the second character data are generated. Data generation step (step (4) in FIG. 7) and the second character data or the original image data are distributed to each one side of the recording medium and printed on both sides based on the generated print data. The processing unit 2 executes the printing process (step (5) in FIG. 7) based on the program, and the text information based on one language laid out from the operation of inputting the document manuscript image is converted to another language. It is possible to programmatically execute a process in which the translated character information and the original document manuscript image are distributed to each side of the same recording medium and printed on both sides in a layout corresponding to the manuscript.

[0070] In the first embodiment and the second embodiment according to the present invention, the case of translating from Japanese to English has been described as an example, but of course, the translation from English to Japanese may also be used. Or it can be a translation from any one language in the world to another. In this case, the translation function is incorporated in the translation unit 5, and the content of the present invention is realized by inputting a manuscript written in the language to be translated from the input unit 1.

Further, in the first embodiment and the second embodiment according to the present invention, the print data is printed after being sent to the storage unit 7 or the storage unit 8 of the printing unit 6. , The print data may also be temporarily stored in the storage unit 3 and may be printed while being sent to the print unit 6 at the time of printing.

Further, in each of the above embodiments, as an example of image processing, an example of creating a business card has been described, but of course, the present invention is not limited to the content of creating a business card, and a pamphlet or the like is created in Japanese. Needless to say, it can be applied to image processing such as translating a product description document (characters, figures, images) into another language with the content translated into a predetermined language and printing on both sides.

[0073] Further, in the image recognition process, by preliminarily dividing the character area with a digitizer or the like, when the original size is large, the accuracy and the recognition process may be speeded up. ..

[Effect of the Invention] As described above, according to the present invention, the image data and the document image data are separated from the original manuscript image data in which the manuscript image is input, and character recognition is performed from the separated document image data. The translated characters are translated into other languages, and further, the print data laid out based on the area-separated document data area information and the second character data is generated, and the translated characters and the input manuscript image are respectively. Since it is distributed to each side of the recording medium and printed on both sides, a simple manuscript image input operation can be used to translate a character image based on one language into another language for layout printing, or to distribute to each side of the same recording medium. It has the effect of being able to print on both sides.

BRIEF DESCRIPTION OF THE DRAWINGS FIG. 1 is a block diagram illustrating a configuration of an image processing apparatus showing a first embodiment of the present invention.

FIG. 2 is a flowchart showing an example of a schematic processing procedure of the first image processing according to the image processing apparatus according to the invention.

FIG. 3 is a diagram illustrating a document image recognition processing state in the image processing apparatus according to the present invention.

FIG. 4 is a flowchart showing an example of a detailed procedure of the recognition processing routine shown in FIG.

FIG. 5 is a flowchart showing an example of another detailed procedure of the recognition processing routine shown in FIG.

FIG. 6 is a block diagram illustrating a configuration of an image processing apparatus showing a second embodiment of the present invention.

FIG. 7 is a flowchart showing an example of a schematic processing procedure of a second image processing according to the image processing apparatus according to the present invention.

[Explanation of code] 1 Input unit 2 Processing unit 3 Storage unit 4 Display unit 5 Translation unit 6 Printing unit 7 Storage unit 9 Recognition unit