基于自蛇模型和小波分析的图像去噪

提出基于自蛇模型和小波分析的集成图像去噪算法,以及峰值信噪比、保护边缘指数的去噪性能综合评价指标。首先利用自蛇模型对含噪图像滤波,然后将处理后的图像进行小波分解,保持低频分量系数,对其高频分量再次利用自蛇模型去噪,最后对处理后的小波系数进行重构,得到去噪后的图像。实验结果表明,本文算法在去噪能力和和保护边缘能力两方面均好于自蛇模型算法和2次迭代自蛇模型算法。

A novel image denoising algorithm based on self-snake model and wavelet analysis

An integrated algorithm based of self-snake model and wavelet analysis, which is able to remove image noise, is proposed, and image denoising performance evaluation can also utilize peak signal noise ratio （PSNR） and preserving edge index （PEI）. In this paper, the self-snake model is firstly used to remove noise of an input image, then the processed image is decomposed by wavelet transform and its three high frequency coefficients are filtered by the self- snake model while maintaining low frequency coefficients, finally, the de-noised image is reconstructed using inverse wavelet transform. The Lena image experimental results indicate that our method has a better performance than self- snake model and twice its iteration in PSNR and PEI