| 基于余弦角距离的蚁群边缘检测算法 |
| |
| 引用本文： | 郑茂垡,刘云飞,周卫红.基于余弦角距离的蚁群边缘检测算法[J].云南民族大学学报(自然科学版),2012,21(1):70-74. |
| |
| 作者姓名： | 郑茂垡 刘云飞 周卫红 |
| |
| 作者单位： | 云南民族大学数学与计算机科学学院,云南昆明,650500 |
| |
| 基金项目： | 云南省教育厅科学研究基金(2011J0492010J071) |
| |
| 摘 要： | 提出一种基于余弦角距离的蚁群边缘检测算法,该算法利用改进的Sobel算子来计算梯度值,综合像素的灰度、梯度、领域特征进行特征提取,以余弦角距离为半径进行聚类,同时通过设置初始聚类中心、启发式引导函数和信息激素提高聚类速度.实验表明该算法优于Sobel、Canny算子和基于欧氏距离的基本蚁群分割算法,是一种有效的方法.
|
| 关 键 词： | 蚁群算法 聚类 图像边缘 特征提取 |
Ant Colony Algorithm for Image Edge Detection Based on the Cosine Angle Distance |
| |
| ZHENG Mao-fa
,
LIU Yun-fei
,
ZHOU Wei-hong.Ant Colony Algorithm for Image Edge Detection Based on the Cosine Angle Distance[J].Journal of Yunnan Nationalities University:Natural Sciences Edition,2012,21(1):70-74. |
| |
| Authors: | ZHENG Mao-fa LIU Yun-fei ZHOU Wei-hong |
| |
| Institution: | (School of Mathematics and Computer Science,Yunnan University of Nationalities,Kunming 650500,China) |
| |
| Abstract: | This paper presents a method of edge detection using the ant colony algorithm based on the cosine of the angle distance.The method adopts an improved Sobel operator to compute the gradient and extract features,including pixel grayscale,gradient and domain feature,and replaces the Euclidean distance by the cosine angle for the clustering radius distance.At the same time,the setting of the initial clustering center,the heuristic guide function and the pheromone can enhance the clustering speed.The experiment shows that the algorithm is an effective method.It is better than which using the Sobel,Canny operator and the basic ant colony segmentation algorithm. |
| |
| Keywords: | ant colony algorithm clustering image edge feature extraction |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
