| 基于极端学习机的胶囊缺陷检测 |
| |
| 引用本文： | 赖大虎,黄宴委.基于极端学习机的胶囊缺陷检测[J].福州大学学报(自然科学版),2012,40(4):489-494. |
| |
| 作者姓名： | 赖大虎 黄宴委 |
| |
| 作者单位： | 福州大学电气工程与自动化学院 |
| |
| 基金项目： | 教育部博士点新教师基金资助项目(No.20113514120007);福建省自然科学基金资助项目(2010J05132);福建省教育厅科研资助项目(JA10034) |
| |
| 摘 要： | 针对胶囊常见的凹陷缺陷进行不变矩分析,提取胶囊的偏心率和圆形度为特征变量,提出一种基于极端学习机的胶囊缺陷检测与识别的方法,对胶囊进行检测分类.仿真结果表明基于极端学习机的胶囊分类算法能很好地区分出具有缺陷的胶囊,分辨正确率接近100%,运算速度比BP神经网络更快,训练过程稳定,也说明所提取的特征能很好区分有凹陷与无凹陷胶囊.
|
| 关 键 词： | 胶囊 特征变量 极端学习机 缺陷 检测 |
Inspection for defected capsules based on extreme learning machine |
| |
| LAI Da-hu,HUANG Yan-wei.Inspection for defected capsules based on extreme learning machine[J].Journal of Fuzhou University(Natural Science Edition),2012,40(4):489-494. |
| |
| Authors: | LAI Da-hu HUANG Yan-wei |
| |
| Institution: | (College of Electrical Engineering and Automation,Fuzhou University,Fuzhou,Fujian 350108,China) |
| |
| Abstract: | In this paper,considering invariant moment for common dent capsules and a method of inspection based on extreme learning machine(ELM)is presented to detect for defected capsules,in which eccentricity and circularity of the capsule are extracted as the features.Simulations indicate the defected capsules can be detected with an approximate accuracy of 100%.The operating speed of ELM is a lot better than that of BP neural network and the detection performance is stable.The results also prove our features are effective to classify the capsules. |
| |
| Keywords: | capsule feature ELM defection inspection |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《福州大学学报(自然科学版)》浏览原始摘要信息 |
| 点击此处可从《福州大学学报(自然科学版)》下载免费的PDF全文 |
