一种简化卷积模板的抗噪型边缘检测算法.doc

一种简化卷积模板的抗噪型边缘检测算法 沈德海，鄂旭，张龙昌 渤海大学 信息科学与技术学院，辽宁 锦州 121013 摘要：针对传统Sobel算法在边缘定位精度不高、抗噪性能差以及提取边缘较粗等不足， 提出了一种简化卷积模板的抗噪型边缘检测算法。算法定义了水平方向、垂直方向、45o方向和135o方向的四个简化卷积模板计算图像梯度。在计算方向梯度时，先对参与梯度计算的像素点采用阈值法进行脉冲噪声判断，将灰度值在设定阈值范围内的点视为噪声点，采用3x3窗口进行中值滤波，然后参与梯度计算，对于非噪声点，用其原值计算梯度；对获得的梯度图像进行细化处理并提取边缘图像。仿真实验表明，本文算法提取的图像边缘较细、定位精度较高，而且对脉冲噪声具有较强的抑制能力，图像整体清晰、噪声边缘较少。算法在边缘检测效果及噪声抑制能力上均优于传统的边缘检测算法及小波模变换算法。 关键词：边缘检测；简化卷积模板；阈值；中值滤波 中图分类号：TP 391.41　文献标识码：A　 文章编号： An Edge Detection Algorithm Of Suppression Noise Based On Simplified Convolution Template SHEN De-hai, E Xu, ZHANG Long-chang Institute of Information Science and Technology, Bahai University, Jinzhou , Liaoning 121013, China Abstract: Aiming at shortcoming of the traditional Sobel algorithm in lower location accuracy, poor noise suppression and coarse edge, proposed an edge detection algorithm of suppression noise?based on simplified convolution template, The algorithm?defined four simplified convolution templates of horizontal direction, vertical direction, 45o direction and 135o direction to calculate image gradient. While calculating direction gradient, makes impulse noise judgment for the point participating in calculation by threshold method, takes the points with gray value in the range of threshold as impulse points, and uses median filter with 3x3 window to obtain their new pixel values. For non-noise points, uses their initial value to calculate direction gradient.?We refine the obtained gradient image, and then extract the image edge. Simulation experiments show that the new?algorithm has high location accuracy, the edge is fine, and has?strong suppressing noise performance; the image is clear, has less noise edge. The new algorithm is better than traditional?edge detection algorithm and?wavelet?transform algorithm in edge effect and suppression noise ability. Keywords: edge detection; simplified convolution template; threshold; median filter 边缘。图像边缘检测精度噪声抑制性能，同时提高噪声抑制性能。传统的边缘检测算法如Sobel、Roberts算子[2]等，其中Sobel和Roberts算法简