| 基于SIFT特征和图割算法的图像分割方法研究 |
| |
| 引用本文： | 徐昱琳,张雷,陈万米,宋鑫坤.基于SIFT特征和图割算法的图像分割方法研究[J].计算机测量与控制,2009,17(12):2491-2493,2499. |
| |
| 作者姓名： | 徐昱琳 张雷 陈万米 宋鑫坤 |
| |
| 作者单位： | 上海大学,机自学院,上海市电站自动化技术重点实验室,上海,200072 |
| |
| 基金项目： | 上海大学创新基金项目，上海市重点学科建设资助项目 |
| |
| 摘 要： | 图割算法是图像分割方法中的一种高效的最优化计算方法,针对图像中目标物体的旋转尺度光照变化导致的分割不准确问题,提出了一种基于SIFT(Scale-Invariant Feature Transform)特征的图割(Graph Cuts)算法;该方法将SIFT特征的尺度旋转不变性和图割算法的准确快速性结合在一起,通过提取图像中物体SIFT特征点做为图割算法的种子点,求解最小能量函数快速从而获得该图像的最优分割;实验结果表明,该方法鲁棒性较好,能准确地分割出目标物体在图像中的轮廓。
|
| 关 键 词： | SIFT特征 图割算法 能量函数 图像分割 种子点 |
Image Segmentation Based on SIFT Feature and Graph Cuts |
| |
| Xu Yulin,Zhang Lei,Chen Wanmi,Song Xinkun.Image Segmentation Based on SIFT Feature and Graph Cuts[J].Computer Measurement & Control,2009,17(12):2491-2493,2499. |
| |
| Authors: | Xu Yulin Zhang Lei Chen Wanmi Song Xinkun |
| |
| Affiliation: | (Shanghai Key Laboratory of Power Station Automation Technology,Shanghai University,Shanghai 20072,China) |
| |
| Abstract: | The graph cuts algorithm is one of high effective optimal methods in the Image segmentations. To improve the accuracy of segmentation when object changes rotations, scale and illumination, a method which combines Scale - Invariant Feature Transform (SIFT) with graph cuts is proposed. The existence of object is recognized by voting processing of SIFT key points and the object region is cut out by graph cut using SIFT key points as seeds by max-flow/min -flow algorithm. Experimental results show this method has a high accuracy and strong robustness. |
| |
| Keywords: | SIFT feature graph cuts algorithm energy function image segmentation seed points |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
