A FNL means De-noise algorithm based on gradient calibration

作者：Li, Jin^*; Wang, Yanwei; Wei, Jie; Wang, Dada; Yu, Hong

来源：International Journal of Advancements in Computing Technology, 2011, 3(9): 147-154.

DOI：10.4156/ijact.vol3.issue9.19

• Computation complexity
• De noise
• Gradient calibration
• Gradient operators
• NL-means
• Parameter estimation method
• Peak Signal to Noise Ratio (PSNR)
• PSNR

In order to overcome the large computing of Non-Local (NL) means de-noise processing, a new method of FNL means de-noise based on gradient calibration is proposed in this paper. Noise variance is estimated from noise image and its gradient. And the optimism parameter is estimated by variance and noise image standard deviation. The gradient operator decreases the HcorrelationH of pixels, so the computation complexity was reduced compared with original NL-Means without performance decline. On the other hand, the optimism parameter is acquired from fuzzy control algorithm to a better de-noise effect and high peak signal to noise ratio (PSNR). Experimental results show that the proposed algorithm is effective and comparing favorable with existing techniques, Practical application shows that this method also proposes a reliable parameter estimation method, and the result is reliable to stitching a large image. At the same time, the processing time is faster than NL means method.

• 出版日期2011
• 单位哈尔滨工程大学