阈值自适应CNN的彩色图像边缘提取-计算机工程与应用.PDFVIP

Computer Engineering and Applications 计算机工程与应用 2014 ，50（21 ） 189 阈值自适应CNN 的彩色图像边缘提取 1 2 3 王 平 ，田 袁 ，胡锡鹏 1 2 3 WANG Ping , TIAN Yuan , HU Xipeng 1.重庆医科大学附属第一医院，重庆 400016 2.重庆大学 计算机学院，重庆 400044 3.总参信息化部训练基地 1.The First Affiliated Hospital of Chongqing Medical University, Chongqing 400016, China 2.College of Computer Science, Chongqing University, Chongqing 400044, China 3.Training Base in Ministry of Information Technology, Headquarters of the General Staff, China WANG Ping, TIAN Yuan, HU Xipeng. Color edge detection based on CNN with adaptive threshold. Computer Engi- neering and Applications, 2014, 50 （21 ）：189-194. Abstract ：Color edge detection based on CNN has attracted many researches. Most existing works utilize fixed threshold based on experience to design CNN templates. However, this method ignores the fact that the human vision system has strong adaptability. Adaptive thresholds are brought into the progress of designing CNN templates, which consider high adaptability of human vision system. Meanwhile, the stability of this algorithm is comprehensively discussed. The algorithm is able to make detected edges be more acceptable by the human vision system. Performance evaluation results validate the efficiency of the proposed algorithm. Key words ：edge detection; cellular neural networks; threshold; adaptability 摘 要：细胞神经网络用于彩色图像边缘提取已经有很多人做了研究。现有的大部分工作都根据经验选取固定阈值 来设计CNN 模板。但这种阈值的选取方法忽略了人眼最小分辨差具有自适应性的特点。在设计图像边缘提取CNN 模板选取阈值时，引入人眼最小阈值差成果，设计出了一组阈值自适应的CNN 模板，同时对设计的阈值自适应算法 的稳定性进行详细的论证。该算法让检测出的边缘更加符合人眼的视觉特性。实验结果证明，该算法效果良好。 关键词：边缘提取；细胞神经网络；阈值；自适应 文献标志码：A 中图分类号：TP391 doi ：10.3778/j.issn. 1002-8331.1401-0454 [3-4] 1 引言 一些问题 ，但在具体应用如：边缘提取中，模板库中 图像中有价值的边界信息被称之为边缘。边缘包