结合Wallis滤波的数字影像特征提取算法

Digital image feature extraction algorithm combined with Wallis filter

针对Wallis滤波在增强影像对比度的同时也增强了影像上噪声信息不利于后续特征提取的问题,提出了1种结合Wallis滤波的数字影像特征提取算法。该算法在Wallis滤波对影像进行处理前,首先采用自适应平滑滤波对影像进行平滑去噪,避免后续噪声被放大;然后,分别采用Moravec算子和相位编组方法对二次滤波后的影像进行特征点、特征线提取。并与原始影像和直接基于Wallis滤波处理后影像的特征提取结果进行对比分析,结果表明,特征提取数目较原始影像有所增加,特征线连续性较好,验证了算法有效性。

Traditional Wallis filter is used to enhance the image contrast,but it increased the noise at the same time.Aiming at this problem,a digital image feature extraction algorithm combined with Wallis filter was proposed.Firstly,the adaptive smoothing filtering was employed for image denoising in the image processing based on Wallis filtering in order to avoid the follow-up noise is amplified.Secondly,the Moravec operator and phase-grouping method were adopted to extract the feature points and feature lines of image after Wallis filtering.Finally,the effectiveness of this algorithm was validated by comparing the extraction results with the original images and the images by the traditional Wallis filtering.The results indicate that the number of feature extraction increases compared with the original image and the continuity of characteristics is relative good,which verifies the validity of the algorithm.