Bark Classification Using RBPNN Based on Both Color and Texture Feature
Zhi-Kai Huang · 2006
Summary In this paper, a new scheme that merges color and texture information for bark image recognition is proposed. The feature vectors concerning color and texture are extracted using the multiresolution wavelet. In addition, the application of these features for bark classification using radial basis probabilistic network (RBPNN) and support vector machine (SVM) has been introduced. Finally, experimental results clearly show that the combining color and texture features that have employed wavelet filter bank for bark classification are more effective than other methods such as Histogram method, Co-occurrence matrices method and Auto-correlation method for bark image.