一种快速边缘检测算法

Fast Edge Detection Algorithm

边缘检测是对图像中像素值的不连续性的度量、检测和定位,是图像分析领域中的一个基础问题.基于斜面分解的非对称逆布局图像表示方法(IDNAM)借鉴斜面拟合和逆布局的思想,使用矩形斜面子模式(RIP子模式)实例的集合来表示图像.基于IDNAM,提出一个RIP子模式内的理想边缘模型,将RIP子模式内的边缘分成五种,并给出了每一种边缘的强度和方向的计算公式.为了消除噪声对边缘检测结果的干扰,提出了RIP子模式内边缘存在性判定条件.根据理想边缘模型和判定条件,提出了一种基于IDNAM的边缘检测算法.理论分析和实验结果均表明,基于IDNAM表示的边缘检测算法的处理速度较传统的边缘检测算法更快.

Edge detection,which measures,checks and captures discontinuity in pixel values in an image,is a basic problem in image analysis.The Inclined plane Decomposition based Non-symmetry and Anti-packing image representation Method（IDNAM）,inspired by the concepts of the inclined plane fitting and anti-packing,uses a set of instances of the Rectangular Inclined Plane sub-pattern（RIP sub-pattern） to represent an image.On the basis of IDNAM,and ideal edge model within a RIP sub-pattern is presented.In the ideal edge model,edges within a RIP sub-pattern are divided into five types,and the methods for computing the edge strength and direction of the edges.The criterions for the existence of an edge within a RIP sub-pattern are presented,to separate between edge and noise.An edge detection algorithm is proposed based on IDNAM,according to the ideal edge model and the criterions.The theoretical analyses and experimental results show that the edge detection algorithm using IDNAM performs faster than the classical ones.