Paper Details

Now a day, digital world increase with bandwidth, handheld devices, storage technologies, social networking sitesand huge volume of images are stored on web. With significantly huge image database it is difficult to mine that data andretrieve relevant images. Image mining work related to this problem in that image retrieval is an important phase. In the fieldof image processing Feature based image retrieval is important research area. It extracts low level features like color ,texture and shape and compute similarity function from images. The main problem of FBIR has been semantic gap betweenlow level visual feature and high level image semantics.In Proposed system architecture HSV space histogram will be used for colour information extraction. Gabor filter will be usefor texture feature extraction and shape feature is using invariant moment method. In this study composite approach ofmultiple feature extraction using hsv histogram, Gabor feature and moment invariant method will be use. Based on theextracted feature Support Vector Machine classification technique is applied. Here classification reduce the search spaceand reduce retrieval time. And SVM accurately classify images in less amount of time than any other classifier. After thatQuery Weight update relevance feedback algorithm has been applied which retrieve more relevant images as per the userfeedback of relevant image .This improves accuracy of finding relevant image for given query image

Keyuri M. Zinzuvadia, Prof. Bhavesh A. Tanawala, Prof. Keyur N.Brahmbhatt, “FEATURE BASED IMAGE RETRIEVAL USING CLASSIFICATION AND RELEVANCE FEEDBACK TECHNIQUE”, International Journal of Advance Engineering and Research Development (IJAERD), Vol. 2, Issue 5, pp. 1253-1262, May 2015.