IOSR Journal of Electronics and Communication Engineering (IOSR-JECE) e-ISSN: 2278-2834,p- ISSN: 2278-8735.Volume 9, Issue 2, Ver. IV (Mar - Apr. 2014), PP 01-07 www.iosrjournals.org www.iosrjournals.org 1 | Page Content Based Image Retrieval Using 2-D Discrete Wavelet with Texture Feature with Different Classifiers Mohankumar C 1 , Madhavan J 2 1 (PG Scholar in Communication Systems, Adhiyamaan College Of Engineering, Hosur, India) 2 (AP in Electronics And Communication Engineering, Adhiyamaan College Of Engineering, Hosur, India) Abstract:In this paper we proposed discrete wavelet transform with texture for content based image retrieval. Our proposed method uses 2-D Discrete Wavelet Transform for reducing the Dimensions of test image and trained images. Further gray level co-occurrence matrix is applied for all test and trained images of LL components of level 2 decomposed images for extract the texture feature of the images. Then similar images are retrieved by using different distance classifiers. Experimental results are performed for Wang’s database and it gives the improved performance for homogeneity with energy property of GLCM of texture feature for Euclidean distance method. Keywords –CBIR, Texture, 2-D Discrete Wavelet Transform, Euclidean distance, Manhattan distance. I. Introduction Content Based Image Retrieval is to retrieve an image from the image database when given a query image. Query Image is the users target image for the searching process. CBIR systems operate in two phases: indexing and searching. In the indexing phase, each image of the database is represented using a set of image attribute, such as color, shape, texture and layout. Extracted features are stored in a feature database. In the searching phase, when a user makes a query, a feature vector for the query is computed. Using a similarity criterion, this vector is compared to the vectors in the feature database. The images most similar to the query are returned to the user. Rapid advances in hardware technology and growth of computer power make facilities for spread use of World Wide Web. This causes that digital libraries manipulate huge amounts of image data. Due to the limitations of space and time, the images are represented in compressed formats. Therefore, new waves of research efforts are directed to feature extraction in compressed domain. Wavelet transform can be used to characterize textures using statistical properties of gray levels of the pixels comprising a surface image [4]. The wavelet transform is a tool that cuts up data or functions or operations into different frequency components and then studies each component with a resolution matched to its scale. In the proposed paper, we use 2-D Discrete Wavelet transform with textured feature images. We also provide a retrieval accuracy strategy for different wavelets. The outline of the paper is as follows. General structure of proposed system is reviewed in section 2. In section 3 discrete wavelet transform is described. Section 4 and 5 discussed about Texture and distance measures. Experimental results and conclusions are presented in section 6 and 7 respectively. II. General Structure Of Proposed CBIR System Fig.1 shows the basic block diagram of Content based image retrieval system. Our Proposed method compares the performance of Content based image retrieval using DWT with Texture for similarity matching of Euclidian distance(L2), Manhattan distance(L1) and Standard Euclidean distance(std L2) method. All train images decomposed using discrete wavelet transform. After DWT, we are taking only low frequency components (LL) of the image for texture feature using GLCM. Then the final feature vectors of all the train images are stored in the database. Same process is done for query image. Finally first 5 similar images are retrieved by using L1, L2, std L2 method Query Image Database Image Fig. 1 Block diagram of proposed system Image Decomposition With DWT GLCM for Texture Feature Image Decomposition With DWT GLCM for Texture Feature Matched Images Similarity Measures Feature Database