本文已被：浏览 1625次 下载 1606次
Received:April 30, 2015 Revised:June 03, 2015
Received:April 30, 2015 Revised:June 03, 2015
中文摘要: 针对被动毫米波(PMMW)图像成像质量差,边界模糊,不易识别的特点,在传统词袋模型图像分类的基础上,提出了利用减法聚类改进FCM聚类算法并将其运用到词袋模型上去,提取视觉单词,利用局部不变量SIFT方法对手枪、匕首和炸药进行了粗分类.实验结果证明,改进的词袋模型能够准确的对违禁品进行分类,识别率平均能达到90%以上,性能优于传统的K均值聚类和原始的FCM聚类算法.
Abstract:For the disadvantage of passive millimeter wave (PMMW) image, such as poor quality, obscure boundary and difficult identification, an improved FCM clustering algorithm is proposed by the subtractive clustering based on the traditional words model. Moreover, with the visual words extracted, the pistol, knives and explosives are briefly by the method of SIFT. Finally, experimental results show that the improved algorithm can be accurately classify the contraband. Furthermore, the average recognition rate can reach more than 90%. Compered with FCM clustering algorithm and K clustering performance, the improved FCM clustering algorithm is excellent.
文章编号： 中图分类号： 文献标志码：
基金项目:陕西省自然科学基金(2014JM1009)
| Author Name | Affiliation |
| CHEN Peng | Postgraduate Brigade, Engineering University of CAPF, Xi'An 710086, China |
| ZOU Tao | Dept. of Information Engineering, Engineering University of CAPF, Xi'An 710086, China |
| Author Name | Affiliation |
| CHEN Peng | Postgraduate Brigade, Engineering University of CAPF, Xi'An 710086, China |
| ZOU Tao | Dept. of Information Engineering, Engineering University of CAPF, Xi'An 710086, China |
引用文本：
陈鹏,邹涛.基于改进FCM聚类算法的违禁品分类.计算机系统应用,2015,24(12):243-248
CHEN Peng,ZOU Tao.Contraband Classification based on Improved FCM Algorithm.COMPUTER SYSTEMS APPLICATIONS,2015,24(12):243-248
陈鹏,邹涛.基于改进FCM聚类算法的违禁品分类.计算机系统应用,2015,24(12):243-248
CHEN Peng,ZOU Tao.Contraband Classification based on Improved FCM Algorithm.COMPUTER SYSTEMS APPLICATIONS,2015,24(12):243-248
