A Methodology For Content-Based Image Retrieval Using Multi-Features Amalgamation

At present,Content-Based Image Retrieval(CBIR) is becoming a hot research topic.It is a retrieval technology based on the vision features,such as the color,texture and shape of the image.It is different from traditional retrieval technology based on the text.This technology directly analyzes image content and extracts image features. These contental features to be built index and be used in retrieval.There are some discusses about the future of CBIR and new technology.Multi-features retrieval technology is a good idea to solve some problems in image retrieve. The multi-features of image retrieval technology has been analyzed in detail.Firstly,the single feature of image includes color,image texture and image shape. The single feature only describes partly attribute of image and influences retrieval efficiency in some conditions.Secondly,when multi-features are used in retrieval,there are three problems want to be resolved. There are image feature selection,withdraw and adjustment of feature weight.At last,the main-color feature based quantification,texture feature based Co-occurrence matrix and Moment invariant are selected in feature retrieval.In multi-features retrieval,the feedback will be used in adjusting weight and re-used in multi-features retrieval.In order to prove the efficience of multi-features retrieval, ten classes experiments have been designed to compare with single-feature and multi-features.The experiment proves that it can greatly improve retrieval efficiency using multi-features.