|
|||||
|
|
| 一种基于有效梯度信息的复杂图像分割方法 | |
| 引用本文： | 潘巍,李晋川,王阳生,杨宏戟.一种基于有效梯度信息的复杂图像分割方法[J].计算机工程与应用,2006,42(18):11-12,64. |
| 作者姓名： | 潘巍 李晋川 王阳生 杨宏戟 |
| 作者单位： | 1. 首都师范大学信息工程学院,北京,100037 2. 四川大学,成都,610065 3. 中国科学院自动化研究所模式识别国家重点实验室,北京,100080 4. Software Technology Research Laboratory,De Montfort University,Leicester,LE1 9BH,England |
| 基金项目： | 国家高技术研究发展计划(863计划) |
| 摘 要： | 论文以集装箱号码图像为例,在分析比较几种流行的图像分割算法后,提出一种新的基于有效梯度信息的图像分割算法,即直接针对梯度图,对目标与背景边界部分的梯度信息进行统计分析,并在此基础上直接得到图像的阈值,完成分割。实验表明,对于类似集装箱号码的复杂图像,论文方法能得到较其他方法更好的分割效果。此外,论文方法有较好的实用性,能广泛应用于多种图像分割领域。 |
| 关 键 词： | 图像分割 梯度信息 阈值 |
| 文章编号： | 1002-8331-（2006）18-0011-02 |
| 收稿时间： | 2006-04 |
| 修稿时间： | 2006-04 |
A Novel Segmentation Algorithm for Complex Images Based on Valid Gradient Information |
|
| Pan Wei,Li Jinchuan,Wang Yangsheng,Yang Hongji.A Novel Segmentation Algorithm for Complex Images Based on Valid Gradient Information[J].Computer Engineering and Applications,2006,42(18):11-12,64. | |
| Authors: | Pan Wei Li Jinchuan Wang Yangsheng Yang Hongji |
| Affiliation: | 1 institute of Information Engineering, Capital Normal University, Beijing 100037;2 Sichuan University,Chengdu 610065; 3 institute of Automation, Chinese Academy of Sciences, Beijing 100080; 4 Software Technology Research Laboratory, De Montfort University, Leicester, LE1 9BH, England |
| Abstract: | Traditional image segmentation algorithms usually can't obtain expected effect facing complex images such as container code images with complex background and bad illumination.A novel segmentation algorithm based on valid gradient information is proposed to solve the problem.By statistical analyzing the gradient information of the boundary between the target and the background,the thresholds can be obtained directly and used to segment the image.The experiment results show that the algorithm can get best performance evaluation.Finally,the algorithm has good practicability and can be used directly in different image segmentation fields. |
| Keywords: | image segmentation gradient information threshold |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ | |