Scale-Space and Edge Detection Using Anisotropic Diffusion
IEEE Transactions on Pattern Analysis and Machine Intelligence
Image selective smoothing and edge detection by nonlinear diffusion
SIAM Journal on Numerical Analysis
Digital Image Processing Algorithms and Applications
Digital Image Processing Algorithms and Applications
Digital Image Restoration
Digital Image Enhancement and Noise Filtering by Use of Local Statistics
IEEE Transactions on Pattern Analysis and Machine Intelligence
Speckle reducing anisotropic diffusion
IEEE Transactions on Image Processing
IEEE Transactions on Neural Networks
Review: Pulse coupled neural networks and its applications
Expert Systems with Applications: An International Journal
| Hi-index | 0.98 |
The effectiveness of anisotropic diffusion based de-noising methods on both noise suppression and edge preservation have been demonstrated in previous research. However, the appearance of the impulse noise like spots in the denoised images becomes one of its limitations due to some high level noise in the noisy images. This paper presents a Pulse Coupled Neural Network (PCNN) based anisotropic diffusion method to solve this problem reducing the 1/f noise in the pinned-type CMOS image sensors (CIS). Different from the traditional methods, pixels are pre-processed by an optimal linear filter according to the time matrix of PCNN before applying an anisotropic filter. Experimental results reveal that the impulse noise like spots are eliminated by the proposed method. And finally, the better performance on both 1/f noise reduction and edge preservation are concluded compared with previous denoising methods, i.e., median filter, Wiener filter, Lee filter and traditional anisotropic diffusion based filters. Furthermore, the results will be applicable to the CIS manufacturing and also contribute to the denoising in still cameras and video cameras.