自适应阈值的Prewitt地质图像边缘检测算法  

Improved Edge Detection Algorithm of Geological Image Based on Prewitt Operator with Adaptive Threshold

作　　者：刘天时[1] 魏雨[1] 李湘眷[1] 

机构地区：[1]西安石油大学计算机学院,西安710065

出　　处：《小型微型计算机系统》2016年第5期1062-1065,共4页Journal of Chinese Computer Systems

基　　金：国家自然科学基金项目(41301480)资助;陕西省教育厅专项科研计划项目(14JK1573)资助;西安石油大学优秀硕士学位论文培育项目(2014yp130612)资助

摘　　要：在地质图像边缘检测中,现有Prewitt相关算法存在边缘识别率低、准确性差、阈值设定随机性大等问题,为此提出一种自适应阈值的Prewitt地质图像边缘检测算法.通过对每个像素点的八组梯度中互相垂直的梯度对求范数,来增强图像边缘;最后取整幅图像的灰度均值作为阈值来识别图像的边缘像素和背景像素.实验表明,相对于现有算法,改进Prewitt算法计算量小,获取的边缘线条细节更加完整清晰.In the edge detection of geological image, the detection rate of existing Prewitt related algorithms is low, the detection accu- racy is poor, and the randomicity of manual threshold is high. Therefore, this paper proposes an improved edge detection algorithm of geological image based on Prewitt operator with adaptive threshold. It enhances the image edge by calculating the norms of mutually perpendicular gradients of eight gradients for each pixel. Finally, it takes the mean gray value of the whole image as the threshold to identify the edge pixels and background pixels. The experiments show that, the calculation of improved Prewitt algorithm is smaller compared with the existing algorithms, and the detail of detected edge is more complete and clear.

关 键 词：PREWITT算子 地质图像 边缘检测 高频强调滤波 灰度均值 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]