视觉感知模型下模糊图像亚像素边缘检测算法  

Subpixel Edge Detection Algorithm for Blurred Image Based on Visual Perception Model

作　　者：孟希志 刘鑫[2] MENG Xi-zhi;LIU Xin(Chengdu College,University of Electronic Science and Technology of China,Chengdu Sichuan 611731,China;School of Computer Science and Engineering,Central South University,Changsha Hunan 410083,China)

机构地区：[1]电子科技大学成都学院,四川成都611731 [2]中南大学计算机学院,湖南长沙410083

出　　处：《计算机仿真》2024年第6期227-231,共5页Computer Simulation

摘　　要：图像边缘中存在大量图像信息,在图像边缘检测中像素级已经无法完全满足图像信息提取需求,往往需要将像素单位提升到亚像素级别,于是提出一种视觉感知模型下模糊图像亚像素边缘检测算法。构建模糊图像还原模型,采用蛙跳算法优化模糊图像,通过最大似然估计原始图像,生成还原后图像。基于突触传递模型,结合视觉感知模型构造视觉感知神经元模型,利用上述模型对图像边缘像素级检测,再引入B样条插值法获取插入点,对图像像素级边缘插值处理,得到图像亚像素级边缘,实现模糊图像亚像素边缘检测。实验结果表明,所提方法FOM值较高,能够获取更加全面的图像边缘信息,检测到的图像边缘更加清晰,细节更加丰富,并且检测时长较短,可广泛应用于图像检测领域。At present,a lot of image information exists in the image edge,and the pixel level in the image edge detection has been unable to fully meet the needs of image information extraction.Therefore,it is necessary to upgrade the pixel unit to the sub-pixel level.In this article,an algorithm for detecting fuzzy image sub-pixel edges was pro⁃posed based on a visual perception model.Firstly,a fuzzy image restoration model was constructed,and then the frog leaping algorithm was adopted to optimize the fuzzy image.Secondly,the original image was estimated by the maximum likelihood,thus generating a restored image.Based on the synaptic transmission model and the visual per⁃ception model,a visual perception neuron model was constructed to detect the pixel level of the image edge,and then the B-spline interpolation method was used to obtain an insertion point.Moreover,the image pixel edge was interpola⁃ted to obtain the image a sub-pixel edge.Finally,the sub-pixel edge detection of fuzzy images was completed.Exper⁃imental results show that the proposed method has a higher FOM value and obtains more comprehensive image edge information,with more rich details as well as shorter detection time.Therefore,this method can be widely used in the image detection field.

关 键 词：视觉感知模型 模糊图像 亚像素 边缘检测 神经元网络 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]