A new technique for CBIR with contrast enhancement using multi-feature and multi class SVM classification

In this research, a new technique For Content Based Image Retrieval (CBIR) with contrast enhancement using multi-feature and multi kernel Support Vector Machine (SVM) method. Color moment (CM), Auto Correlogram (AC), Discrete Wavelet Transform (DWT), Gabor Filter (GF) features are proposed. We extended the previous work which used binary SVM classifier and color features. First of all take a query image, then the appearance of the image is improved using contrast adjustment. For its color feature, apply color moment method, convert RGB into HSVcolor space and make feature vector (mean). Extract texture features using GF, DWT and inverse difference moment (IDM). Skewness and Kurtosis are extracted for shape feature. Variance, root mean square (RMS) is extracted for color feature. After extracting the image feature, we used a supervised learning technique which is known as Multi kernel SVM to determine the optimal outcomes. After combining the features and classify the data. And finally compare the results with the previous method. The proposed method gives better accuracy and precision value. This work is simulated on MATLAB2012 simulator.