IMAGE PROCESSING SYSTEM, IMAGE PROCESSING METHOD, AND IMAGE PROCESSING PROGRAM

An image processing system according to one embodiment includes a feature quantity calculation unit, a classification unit, a score calculation unit, and an output unit. The feature quantity calculation unit calculates a feature quantity for each of a plurality of candidate regions extracted as a candidate for a text region from a plurality of original sample images. The plurality of original sample images include one or more text images containing a text region and one or more non-text images not containing a text region. The classification unit classifies the plurality of candidate regions into a plurality of categories based on the feature quantity. The score calculation unit calculates, for each category, a score indicating a frequency of appearance of the candidate region to which an annotation indicating extraction from the text image is added. The output unit outputs the score of each category as category information.