Bark Classification Using RBPNN Based on Gabor Filter in Different Color Space

This paper proposed a new method of extracting texture features based on Gabor wavelet in different color space. In addition, the application of these features for bark classification applying radial basis probabilistic network (RBPNN) and SVM (support vector machine) has been used. To extract the bark texture features, Gabor filter the image has been filtered with four orientations and six scales filters, and then the mean and standard deviation of the image output are computed. In addition, apart from these features of parameter of Gabor filter features, other features such as color distribution angles were also extracted. Finally, the combined Gabor feature vectors and color distribution angles are fed up into RBPNN and SVM for classification. The performance of colour space features is found to be better than that of the features which just extracted from grey image. Experimental results show that features extracted using the proposed approach can be used for bark texture classification.