Wireless Capsule Endoscopy Images Enhancement by Tensor Based Diffusion

To enhance the contrast and the details of the wireless capsule endoscopy images, which are used to diagnose the status of the human gastrointestinal tracts, we propose a tensor based diffusion method in this paper. After analyzing the structure tensor of the image in RGB color space, we focus on the properties of the nonlinear anisotropic diffusion. Then we design two diffusion strength functions to determine the anisotropic diffusion according to the local characteristics of the wireless capsule endoscopy images. Experimental results on real wireless capsule endoscopy images indicate effective enhancement of details and contrast by our new approach

[1]  Fionn Murtagh,et al.  Gray and color image contrast enhancement by the curvelet transform , 2003, IEEE Trans. Image Process..

[2]  KokKeong Tan,et al.  Enhancement of color images in poor visibility conditions , 2000, Proceedings 2000 International Conference on Image Processing (Cat. No.00CH37101).

[3]  Joachim Weikert,et al.  Multiscale Texture Enhancement , 1995, CAIP.

[4]  Vijayan K. Asari,et al.  An Illuminance-Reflectance Model for Nonlinear Enhancement of Color Images , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Workshops.

[5]  Jinhui Qin,et al.  A new wavelet-based method for contrast/edge enhancement , 2003, Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429).

[6]  K K Tan,et al.  Physics-based approach to color image enhancement in poor visibility conditions. , 2001, Journal of the Optical Society of America. A, Optics, image science, and vision.

[7]  Guillermo Sapiro,et al.  Anisotropic diffusion of multivalued images with applications to color filtering , 1996, IEEE Trans. Image Process..

[8]  Douglas G. Adler,et al.  Wireless Capsule Endoscopy , 2003 .

[9]  Jitendra Malik,et al.  Scale-Space and Edge Detection Using Anisotropic Diffusion , 1990, IEEE Trans. Pattern Anal. Mach. Intell..