Indian Journal of Science and Technology

Abstract

Objectives: Nowadays, the capacity of digital image information is rapidly surging. The computational complexity of retrieving images from database also increases. Methods/Statistical Analysis: Texture and colour are the most important components of visual information which can be used effectively to reduce the complexity. This paper presents Content-Based Image Retrieval System (CBIR) based on texture and colour similarity. The RGB colour space and the colour histogram are used as the colour feature of each image. The texture of each image is obtained by applying gray level co-occurrence matrix. Findings: Based on the similarity between image features CBIR methods retrieve images accurately from the image database. But the traditional system will work well only for the data set which has more dissimilarity. In this study, based on combining the Gaussian Mixture Model(GMM) with k-means clustering algorithm, a new hybrid algorithm for clustering is proposed. A one to one matching scheme is used to compare the query and target image on the basis of all the features extracted. This hybrid Gaussian mixture model will provide more accurate retrieval in the case of the dissimilarity between the image data set is very low. The proposed system is capable of working fewer dissimilarity data set as well more dissimilarity data. Applications/Improvements: The proposed hybrid retrieval method provide more accurate retrieval with the precision measures of 98% and also more robustness with retrieval of 95%.

Keywords: Content-Based Image Retrieval (CBIR), Co-occurrence Matrix, Expectation-Maximization (EM) Algorithm, Feature Extraction, Gaussian Mixture Model (GMM), K-Means Clustering Algorithm