Texture Feature Extraction Algorithm Based On Wavelet

Texture is a perception of the natural phenomenon from the visual system. It iswidespread in nature as one of the basic properties of the surface, which always be used asthe improtant characteristics to describe and distinguish the different objects. Textureanalysis is a hotspot in image processing, since texture feature extraction is the primaryproblem of it, has been the focus of attention. A new method of texture feature extractionbased on co-occurrence matrix in dual-tree complex wavelet domain was proposed in thispaper. The paper analyzed the image texture features with clustering, and apply into imageretrieval. The main work and innovations are as follows:1.The paper reproduce the texture feature extraction methods of GLCM and DT-CWT.In GLCM, it chooses energy, entropy, inertia and local stationary as the values of thetexture feature. The structural parameters are determined by examing the impact of thetexture feature. The experimental results showed GLCM is simple and less computation. InDT-CWT, by comprised the CWT and DT-CWT, we verify DT-CWT as the best way toanalysis the images texture through the multi-scale and multi-directions.2.A new method of texture feature extraction based on co-occurrence matrix indual-tree complex wavelet domain was proposed in this paper. It uses dual-tree complexwavelet to decomposed the image texture with the filters which satisfy both orthogonal andreconstruction. The low-frequency sub-images produced by the multilayered dual-treecomplex wavelet decomposition of texture images were utilized to calculate theco-occurrence in different directions for extracting the image texture features. Thehigh-frequency sub-images produced by the multilayered dual-tree complex waveletdecomposition of texture images were utilized to calculate the co-occurrence in differentdirections for extracting the image texture features. The experimental results showed thatthis method can effectively extract the texture features in the multi-scale andmulti-directions.3.The paper uses clustering to do the performance analysis for the feature vectorswhich extract from the GLCM, DT-CWT and the new method. Then make each texturefeature vectors as a sample of a cluster, all the different types of feature vectors form thecluster. By comparison the three methods of image texture extraction with internal distance,the distance between the cluster and the ratio of them, the experimental results show that the extracted texture features had favorable cluster separability and kept otherness ofsamples in the same cluster.4.The paper apply the GLCM, DT-CWT and the new method into image retrieval.Comparised three methods with the average precision of image retrieval, the experimentalresults show that the new method has efficiency calculation, easy operation and improvethe accuracy of image retrieval effectively.