【摘要】 从分数阶微分和小波分解的特点出发,提出一种用于图像增强的FWE(Fractional Differential and Optimal Wavelet De-composition Used in Image Enhancement)方法,即通过在一定分解层数范围内分别计算图像经小波分解所得各分量信息熵最大值所对应的分解层来确定一个最优分解层N,使用新提出的分数阶微分掩模对原始图像以及图像经小波分解与重构的第N层各分量信号有针对性地进行处理.对处理结果进行叠加,可深度地保留图像原有特征,同时对灰度变化不明显区域图像纹理细节也得到增强.从实验对比结果来看,这种方法和一定范围内最优小波分解层的确定是可行的.更多还原

【Abstract】 Starting from the characteristic of fractional differential and wavelet decomposition,a method of image enhancement named FWE(Fractional Differential and Optimal Wavelet Decomposition Used in Image Enhancement) was proposed,which determined a optimal decomposition level N by respectively calculating the maximum entropy of components generated by image wavelet decomposition,then,the proposed new fractional differential mask to targeted process the original image and the N level components signal which abtained by image wavelet decomposition and reconstruction was utilized.Finally,the results were merged so that it could furthest preserve image original feature,and also enhance texture details in those areas that gray-level did not change evidently.Experimental comparison results show that this method and the determination of optimal wavelet decompositon level in a certain range is feasible.更多还原