A Clothing Image Retrieval System Based on Improved Itti Model
Aiming at the problems of Itti visual attention model like inadequate feature extraction, complex feature synthesis process and feature incompatible with existing retrieval system, a better Itti model is proposed to improve the low-level visual features, image segmentation and interesting area in this paper. And then the improved Itti visual attention model is introduce to content based Clothing image retrieval system, the experimental results show our system has obvious advance on the accuracy of retrieval effect than the existing similar system.
KeywordsImage retrieval Texture character Image segmentation Interesting area
This work was by Guangdong Provincial Scientific Research Fund of China (No. 2016A030313717); Natural Scientific Research Fund of China (No. 61472135).
- 2.Forczmański, P., Czapiewski, P., Frejlichowski, D.: Comparing clothing styles by means of computer vision methods. Comput. Vis. Graph. 86(7), 203–211 (2014)Google Scholar
- 4.Chuanbo, H., Zhong, J.: Image retrieval using multiresolution analysis of visual attention. J. Image Graph. 16(9), 1656–1663 (2011)Google Scholar
- 6.Zhang, J., Shen, L., David, D.: A survey of image retrieval based on visual perception. Acta Electronica Sinica 36(3), 494–499 (2008)Google Scholar
- 7.Zhang, J., Shen, L.S., Gao, J.J.: Regions of interest detection based on visual attention mechanism. Acta Photonica Sinica 38(6), 1561–1565 (2009)Google Scholar
- 8.Zeng, Z., Zhang, X., Cui, J., et al.: A novel image retrieval algorithm based on color and distribution of prominent interest points. Acta Photonica Sinica 35(2), 308–311 (2006)Google Scholar
- 11.Wei, N., Geng, G.H., Zhou, M.Q.: An overview of performance evaluation in content-based image retrieval. J. Image Graph. 9(11), 1271–1276 (2004)Google Scholar