[1]吴家伟,严京旗,方志宏,等.基于图像显著性特征的铸坯表面缺陷检测[J].智能系统学报,2012,7(01):75-80.
 WU Jiawei,YAN Jingqi,FANG Zhihong,et al.Defect detection on a steel slab surface based on the characteristics of an image’s saliency region[J].CAAI Transactions on Intelligent Systems,2012,7(01):75-80.
点击复制

基于图像显著性特征的铸坯表面缺陷检测(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第7卷
期数:
2012年01期
页码:
75-80
栏目:
出版日期:
2012-02-25

文章信息/Info

Title:
Defect detection on a steel slab surface based on the characteristics of an image’s saliency region
文章编号:
1673-4785(2012)01-0075-06
作者:
吴家伟1严京旗1方志宏2夏勇2陆敏健3
1.上海交通大学 图像处理与模式识别研究所,上海 200030;
2.宝山钢铁股份有限公司研究院,上海 201900;
3.宝山钢铁股份有限公司 设备部,上海 201900
Author(s):
WU Jiawei1 YAN Jingqi1 FANG Zhihong2 XIA Yong2 LU Minjian3
1.Institute of Image Processing & Pattern Recognition, Shanghai Jiao Tong University, Shanghai 200030, China;
2.Institute of Baoshan Iron & Steel Co., Ltd., Shanghai 201900, China;
3.Equipment Department of Baoshan Iron & Steel Co., Ltd., Shanghai 201900,China
关键词:
铸坯表面缺陷检测显著性区域特征提取Gabor小波Adaboost分类器
Keywords:
steel slab surface defect detection saliency region feature extraction Gabor wavelet Adaboost classifier
分类号:
TP391.4
文献标志码:
A
摘要:
针对钢铁铸坯表面检测的缺陷复杂性问题,从图像处理及图形特征角度提出一种基于显著性区域特征的算法.该算法首先对源图像进行显著性特征区域处理和Gabor小波滤波处理,得到了对应的特征图像;然后再将2幅图像中的特征区域进行融合,得到可信度较高的缺陷特征区域图像;最后在缺陷区域中用训练好的Adaboost分类器检测缺陷,得到最终的缺陷定位结果.该算法结合了显著性特征和Gabor小波特征,既缩小了Adaboost分类器的搜索范围,也提高了排除伪缺陷的能力,具有较快的定位速度和较高的准确率.实验结果表明,该算法能获得较好的效果,具有较高的实用价值.
Abstract:
In considering complex defect conditions in steel slab surface detection, a new defect detection method based on the saliency region was presented from the viewpoint of image processing and graphics features. First, by the processing of saliency region characteristics and Gabor wavelet filtering, the feature image was obtained, and then the characteristic regions in the two images were fused to obtain a highly reliable image of the defect region characteristics. Finally, the defect was detected by a welltrained Adaboost classifier in the fused defect region, thereby obtaining the final defect positioning result. The algorithm combines saliency region characteristics and Gabor wavelet features; it not only narrows the search range of the Adaboost classifier, but also improves the ability to exclude pseudodefects. Consequently, it has faster positioning speed and higher accuracy. The algorithm performed well in the experiment and possesses high practical value. 

参考文献/References:

[1]MA Yufei, ZHANG Hongjiang. Contrastbased image attention analysis by using fuzzy growing[C]//Proceedings of the 11th ACM Intemational Conference on Multimedia. New York, USA: ACM, 2003: 374381.
 [2]KO B C, KWAK S Y, BYUN H. SVMbased salient region(s) extraction method for image retrieval[C]//Proceedings of the 17th International Conference on Pattern Recognition. Washington, DC, USA: IEEE Computer Society, 2004: 977980.
[3]ITTI L, KOCH C, NIEBUR E. A model of saliencybased visual attention for rapid scene analysis[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20(11): 12541259.
[4]GOFERMAN S, ZELNIKMANOR L, TAL A. Contextaware saliency detection[C]//2010 IEEE Conference on Computer Vision and Pattern Recognition. San Francisco, USA, 2010: 23762383.
[5]ZHAI Y, SHAH M. Visual attention detection in video sequences using spatiotemporal cues[C]//Proceedings of the 14th Annual ACM International Conference on Multimedia. New York, USA: ACM, 2006: 815824.
[6]CHENG Mingming, ZHANG Guoxin, MITRA N J, et al. Global contrast based salient region detection[C]//2011 IEEE Conference on Computer Vision and Pattern Recognition. Providence, USA, 2011: 409416.
[7]钟微,谢雪梅,石光明.一种灵活的图像频谱分割与去噪方法[J].西安电子科技大学学报, 2007, 34(6): 935938.
ZHONG Wei, XIE Xuemei, SHI Guangming. Image spectrum segmentation and denoising based on multichannel nonuniform filter banks[J]. Journal of Xidian University, 2007, 34(6): 935938.
[8]张红梅,卞正中,郭佑民,等.感兴趣区域高效提取算法[J].软件学报, 2005, 16(1): 7788.
ZHANG Hongmei, BIAN Zhengzhong, GUO Youmin, et al.〖LL〗An efficient approach to extraction of region of interest[J]. Journal of Software, 2005, 16(1): 7788.
[9]HOU Xiaodi, ZHANG Liqing. Saliency detection: a spectral residual approach[C]//2007 IEEE Conference on Computer Vision and Pattern Recognition. Minneapolis, USA, 2007: 18.
[10]毕为民,孙才新,姚陈果.基于门限值小波包变换抑制局部放电白噪干扰[J].重庆大学学报, 2003, 26(6): 5355.
 BI Weimin, SUN Caixin, YAO Chenguo. Wavelet packet decomposition based on entropy threshold for whitenoise rejection in PD signal[J]. Journal of Chongqing University, 2003, 26(6): 5355.

相似文献/References:

[1]逄增治,郑修楠,李金屏.全钢子午线轮胎X光图像的缺陷检测研究现状[J].智能系统学报,2019,14(04):793.[doi:10.11992/tis.201806014]
 PANG Zengzhi,ZHENG Xiunan,LI Jinping.Research status of defect detection in X-ray images of all-steel radial tires[J].CAAI Transactions on Intelligent Systems,2019,14(01):793.[doi:10.11992/tis.201806014]

备注/Memo

备注/Memo:
收稿日期:2011-11-23.
基金项目:国家自然科学基金资助项目(60873137).
通信作者:严京旗.        E-mail:jqyan@sjtu.edu.cn.
 作者简介:
吴家伟,男,1988年生,硕士研究生,主要研究方向为图像处理、机器学习与生物特征识别.
严京旗,男,1975年生,副教授.参与并主持了多项国家自然科学基金项目.主要研究方向为图像图形综合技术、可视计算、三维生物特征识别等.
 方志宏,男,1968年生,副教授,博士.主要研究方向为冶金自动化、图像处理、信号处理和电子技术的应用等.
更新日期/Last Update: 2012-05-07