Image processing apparatus and method, and non-transitory computer readable medium

摘要

An image processing apparatus includes an identifier that calculates, between multiple items of first document data and multiple items of second document data, a first degree of similarity of a pair of each page of the first document data and each page of the second document data, based on a page order of the first and second document data, extracting a pair of pages of which a second degree of similarity is calculated based on the first degree of similarity, calculating the second degree of similarity of the extracted pair of pages based on images of the first and second document data, and identifies a page of the second document data that corresponds to a page of the first document data, based on the second degree of similarity.

主权项

1. An image processing apparatus comprising:
an identifier that: (i) calculates, between a plurality of items of first document data and a plurality of items of second document data, a first degree of similarity of a pair of each page of the first document data and each page of the second document data, based on a page order of the first and second document data, the first degree of similarity being calculated separately for every page of the first document data with respect to every page of the second document data, (ii) extracts a pair of pages of which a second degree of similarity is calculated based on the first degree of similarity, and calculates the second degree of similarity of the extracted pair of pages based on images of the first and second document data, and (iii) identifies a page of the second document data that corresponds to a page of the first document data, based on the second degree of similarity.