An Efficient Classification Algorithms for Image Retrieval Based Color and Texture Features

Abstract

            Content-Based Image Retrieval CBIR system commonly extracts retrieval results respecting to the similarities of the extracted feature of the given image and the candidate images. The proposed system presented a comparative analysis of five types of classifiers which used in CBIR. These classifiers are Multilayer Perceptron (MP), Sequential Minimal Optimization (SMO), Random Forest (RF), Bayes Network (BN) and Iterative Classifier Optimizer (ICO). It has been investigated to find out the best classifier in term of performance and computation to be the suitable for image retrieval. The low level image features which include texture and color are used in the proposed system. The color features involve color-histogram, color-moments and color-autocorrelogram while texture features involve wavelet transform and log Gabor filter. Also the system will include hybrid of texture and color features to get efficient image retrieval. The system was tested using WANG database, and the best average precision achieved was (85.08%) when combining texture and color features and using the (RF) classifier.