Document Image Retrieval from Incomplete Queries Using Texture Features

Abstract

        Document image retrieval (DIR) is an important part of many document image processing systems such as paperless office systems, digital libraries and so on. It helps the users to find out the most similar document images from a document image database. Most of the researches have been carried out with complete queries which were present in the database, but in many cases distorted or incomplete images can be encountered. This distortion or incompetence is due to some missing information, some undesirable objects, blurring, noise due to document printing, scanning etc. This paper describes an approach for retrieval of incomplete and distorted document images based on visual features using texture information for retrieval from large document image database. A Gray Level Co-occurrence Matrix (GLCM) features for texture analysis were proposed and provide a comprehensive experimental evaluation.