A Method of the Extraction of Texture Feature
In order to understand the emotional information of the color image, research focus has been shifted from designing sophisticated low-level feature extraction algorithms to reducing the ‘semantic gap’ between the visual features and the richness of human perception. In this paper, we firstly get the ROI using the Eye tracker and divide every image into two regions including Regions of Interest (ROI) and Non- Regions of Interest (Non-ROI). Secondly, we use the analytical hierarchy process (AHP) to provide a systematical way to evaluate the fit weights of ROI and Non-ROI. Finally, using the improved GLCM, we extract the texture feature of the two regions including ROI and Non-ROI, and get the whole texture feature. The algorithm is tested that the average detection rate of the proposed method is up to the same method using GLCM.
KeywordsRegions of Interest (ROI) Texture feature Gray Level Co-occurrence Matrix (GLCM) Analytical Hierarchy Process (AHP) Weight
Unable to display preview. Download preview PDF.
- 1.Ramey, N.A., Ying, H.S., Irsch, K.: A novel haploscopic viewing apparatus with a three-axis eye tracker. Journal of AAPOS.2008.01.019Google Scholar
- 3.Hough, P.V.C.: Methods and means for recognizing complex patterns. U.S. Patent 3069654 (1962)Google Scholar
- 7.Cheng, S.-C., Chen, M.-Y., Chang, H.-Y., Chou, T.-C.: Semantic-based facial expression recognition using analytical hierarchy process (2007)Google Scholar
- 8.Haralick, R.M., Shanmugam, K., Dinstein, I.: IEEE Trans. Syst. Man Cybern. 3, 610–621 (1973)Google Scholar
- 10.Weszka, J.S., Dyer, C.R., Rosenfeld, A.: IEEE Trans. Syst. Man Cybern. 5, 269–285 (1976)Google Scholar
- 11.Al-Janobi, A.: Pattern Recogn. 34, 171–180 (2001)Google Scholar
- 12.Schmid, C., Mohr, R.: IEEE Transactions on Pattern Analysis and Machine Intelligence. 19(5), 530 (1997)Google Scholar
- 13.Tian, Q., Sebe, N., Lew, M.S., et al.: Journal of Electronic Imaging. 10(4), 835 (2001)Google Scholar
- 14.Moghaddam, B., Biermann, H., Margaritis, D.: Defining image content with multiple regions of interest. In: Proc. IEEE Workshop on Content-Based Access of Image and Video Libraries (CVPR 1999), p. 350 (1999)Google Scholar