A Feature-Based Document Image Retrieval Method

Abstract

A document image retrieval method based on the paragraph feature combining up with the relative difference of local pixel distributions and high-dimensional data index structure is developed in the article .First, the definitions of paragraph feature and relative difference of local pixel distributions are given, then the extraction method is described in detail, so is the retrieval method based on the two features. As a global feature, the paragraph feature combined with the relative difference of local pixel distributions, which is a local feature, could describe the document image sufficiently and give a good distinguish. High-dimensional data index structure used in the method could greatly improve the velocity. Based on them, an efficient retrieval method is derived.