改进的Sobel算子彩色图像边缘检测  

Color image edge detection based on improved Sobel algorithm

作　　者：孙蔚[1,2] 王靖[1] 王波[1] 

机构地区：[1]南京人口管理干部学院信息科学系,江苏南京210042 [2]南京航空航天大学自动化学院,江苏南京210016

出　　处：《电子技术应用》2013年第2期128-129,133,共3页Application of Electronic Technique

基　　金：江苏省高校自然科学研究项目(09KDJ510006);南京人口学院科研基金项目(2010C12);南京人口学院教学改革研究项目(2010TXGGB12)

摘　　要：为了解决传统灰度图像边缘检测中容易出现的边缘定位偏差、边缘丢失以及边缘不连续等问题,结合传统的Sobel梯度边缘检测方法和图像阈值分割技术,提出了一种改进的Sobel算子彩色图像边缘检测方法。通过对比试验结果表明,该方法可以有效地降低色彩边缘的误检率,一定程度上提高了边缘检测器的性能。The traditional image edge detection methods have many shortcomings such as with edge position deviation, edge lost and with discontinuous edges ere. In order to solve such problems a novel method was provided in this article which combined the traditional Sobel gradient edge detection method and image threshold segmentation technique. Compared with the traditional image edge detection methods, it reduces the color edge detection error rate and improves the edge detection performance.

关 键 词：SOBEL 阈值分割 边缘检测 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]