Improvement in Performance of Image Retrieval using Various Features in CBIR System

Abstract

Content-Based image retrieval systems (CBIR) have become very popular for browsing, searching, and retrieving images from a large database of digital images as it requires relatively less human interference. In Content-based image retrieval system, visual feature. Color, texture and shape features have been the primitive image descriptors in CBIR systems. By using only color, texture or shape features, cannot get high precision. So, propose a new content-based image retrieval method that uses combination of color, shape and texture feature to get high precision. By using techniques like Image Processing, Data Mining, Machine Learning and Database for extracting color features, texture features and shape features, In this paper discuss the using various features and technique to possible get best precision as well as less computational complexity and good retrieval accuracy.