An image processing apparatus and method, and an image evaluation device and method

In image processing according to the prior art, the important part of photographic image data (referred to herein as the object) could not be determined and therefore required human participation. A computer 21 which is the core of image processing calculates an edginess which is an image variation from a differential value of data for adjacent picture elements in a step SA110, and determines object picture elements by selecting only images with a large variation in steps SA120, SA130. As optimum parameters for contrast correction and lightness compensation are calculated from image data for object picture elements in steps SA310-SA330, image processing indicators based on object picture elements are determined, and optimum image processing can be performed automatically. After summing a luminance distribution for each area of the image, which is a feature amount, while uniformly selecting picture elements in a step SB110, a reevaluation is performed by a weighting determined for each area in a step SB120, and a luminance distribution strongly influenced by the luminance distribution of the photographed object is thus obtained with uniform sampling. After determining the intensity of this luminance distribution in steps SB130-SB150, the image data is converted in a step SB160, and image processing can therefore be performed with optimum intensity while reducing the processing amount.