Application of Gray Level Variation Statistic in Gastroscopic Image Retrieval

Content-based medical image retrieval is getting more and more importance in aspect of clinical assistant diagnose. In this paper a system for gastroscopic image retrieval is developed which is available to support clinical decision making. First a new method based on texture feature is proposed which statistic the gray level variation of each pixel in 3x3 domain. And then Earth Mover’s Distance is used to calculate the dissimilarity. Meanwhile¿a method combining both color and texture is proposed to carry out integrate retrieval. Finally, some contrast experiments are designed in the retrieval accuracies¿the rank and the execution time. The comparison of the experimental results shows that the approach proposed in this paper is effective.

[1]  Te-Er Ba,et al.  [Medical image retrieval based on low level feature fusion and relevance feedback]. , 2008, Zhongguo yi liao qi xie za zhi = Chinese journal of medical instrumentation.

[2]  L.-H. Chen,et al.  Colour image retrieval based on primitives of colour moments , 2002 .

[3]  Xiaoying Tai,et al.  Image Retrieval Based on Color and Texture , 2006, 2006 Fifth Mexican International Conference on Artificial Intelligence.

[4]  Hayit Greenspan,et al.  Context-based image modelling , 2002, Object recognition supported by user interaction for service robots.

[5]  C. Tomasi.  The Earth Mover's Distance, Multi-Dimensional Scaling, and Color-Based Image Retrieval , 1997 .

[6]  Luo Si,et al.  A study of methods for normalizing user ratings in collaborative filtering , 2004, SIGIR '04.

[7]  Prabir Kumar Biswas,et al.  Texture image retrieval using new rotated complex wavelet filters , 2005, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[8]  Jau-Ling Shih,et al.  Color Image Retrieval Based on Primitives of Color Moments , 2002, VISUAL.

[9]  Wang Li-dong,et al.  Medical Image Retrieval Based on Color-Texture Algorithm and GTI Model , 2008, 2008 2nd International Conference on Bioinformatics and Biomedical Engineering.

[10]  Mohd Sapiyan Baba,et al.  Automatic Multilevel Medical Image Annotation and Retrieval , 2008, Journal of Digital Imaging.

[11]  Hongyu Yao,et al.  An efficient approach for texture-based image retrieval , 2003, International Conference on Neural Networks and Signal Processing, 2003. Proceedings of the 2003.

[12]  Xiaoying Tai,et al.  Image Retrieval Based on Color and Texture , 2007, Fourth International Conference on Fuzzy Systems and Knowledge Discovery (FSKD 2007).

[13]  Mika Rautiainen,et al.  Temporal color correlograms for video retrieval , 2002, Object recognition supported by user interaction for service robots.