Title :
Soft-Threshold De-noising Method of Medical Ultrasonic Image Based on PCNN
Author :
Ye-Cai Guo ; Long-qing He ; Shao-Bo Wang
Author_Institution :
Nanjing Univ. of Inf. Sci. & Technol., Nanjing, China
Abstract :
Based on the analysis of the speckle noise´s properties, a soft-threshold de-noising method of medical ultrasonic image based on PCNN was proposed. In the proposed method, wavelet transform can produce the coefficients which contain the distinct characteristics of input information and make coarse-to-fine multi-resolution analysis for signal, and PCNN can recognize signals, it is realized that PCNN recognizes the coefficients of high frequency in wavelet domain, and then the wavelet coefficients are processed by corresponding methods, the speckle noises can be removed. The experimental results show that the Peak Signal to Noise Ratio (PSNR) is higher and the details of images are kept as more as possible, meanwhile, the edge blur phenomenon caused by wavelet threshold de-noising is improved.
Keywords :
image denoising; medical image processing; neural nets; coarse-to-fine multiresolution analysis; medical ultrasonic image; peak signal to noise ratio; pulse coupled neural networks; soft-threshold denoising method; wavelet transform; Biomedical imaging; Character recognition; Image analysis; Noise reduction; PSNR; Signal processing; Speckle; Wavelet analysis; Wavelet domain; Wavelet transforms; PCNN; PSNR; speckle noises; wavelet transform;
Conference_Titel :
Artificial Intelligence and Computational Intelligence, 2009. AICI '09. International Conference on
Conference_Location :
Shanghai
Print_ISBN :
978-1-4244-3835-8
Electronic_ISBN :
978-0-7695-3816-7
DOI :
10.1109/AICI.2009.372
