Automatic web page logo detection (Logo matching using semantic relevance feedback)

Abstract

In the past few decades many information's are stored in World Wide Web as web pages and documents, it is increased by huge amount of data so the problem persist for searching a particular document. There are various document image retrieval image methods are available such as classification, clustering and graph techniques are designed to detect the problems in document image retrieval system. This research is concerned with study and analysis of focusing document image retrieval and logo matching in journal database. There are various national and international journals are available in online to representing their logo in document. Retrieval framework is effective not only in improving retrieval performance in a given query session, but also utilizes the knowledge learnt from previous queries to reduce the number of iterations in following queries. This paper describes methods and techniques for document image retrieval analysis, logo matching and survey includes the current state of research problems in information retrieval, document image retrieval, relevance feedback and logo based text retrieval.