Fabric defect detection based on the saliency map construction of target-driven feature

被引:18
作者
Guan, Shengqi [1 ]
Shi, Hongyu [2 ]
机构
[1] Xian Polytech Univ, Coll Mech & Elect Engn, Xian, Shaanxi, Peoples R China
[2] Xian Polytech Univ, Coll Comp Sci, Xian, Shaanxi, Peoples R China
关键词
Fabric defect; task-driven feature; saliency map construction; defect detection; VISUAL-ATTENTION; TEXTILE FABRICS; INSPECTION; SEGMENTATION;
D O I
10.1080/00405000.2017.1414669
中图分类号
TB3 [工程材料学]; TS1 [纺织工业、染整工业];
学科分类号
0805 ; 080502 ; 0821 ;
摘要
In inspection of fabric surface quality in production line, small defects have to be detected in a large background. In this paper, a new method is put forward to detect fabric surface defect by target-driven features. First of all, surface defect feature of fabric is analyzed; and then, area feature of and number feature of defects are used as tasks, which drive to enhance saliency of defective regions and to form feature saliency maps; finally, by using threshold segmentation, fusion, and filtering, fabric defect is gained from the feature saliency maps. Experiments show that the detection algorithm, compared with classic defect algorithm, can achieve accurate segmentation of the surface defects, better anti-noise ability, higher detection accuracy, which has a strong applicability on the fabric defect detection, and provides the possibility for realizing automatic detection of textile industrial product surface defect.
引用
收藏
页码:1133 / 1142
页数:10
相关论文
共 20 条
[1]   Strip Steel Surface Defect Recognition Based on Novel Feature Extraction and Enhanced Least Squares Twin Support Vector Machine [J].
Chu, Maoxiang ;
Wang, Anna ;
Gong, Rongfen ;
Sha, Mo .
ISIJ INTERNATIONAL, 2014, 54 (07) :1638-1645
[2]   AUTOMATED INSPECTION OF TEXTILE FABRICS USING TEXTURAL MODELS [J].
COHEN, FS ;
FAN, ZG ;
ATTALI, S .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1991, 13 (08) :803-808
[3]   Neural Mechanisms of Selective Visual Attention [J].
Moore, Tirin ;
Zirnsak, Marc .
ANNUAL REVIEW OF PSYCHOLOGY, VOL 68, 2017, 68 :47-72
[4]   Fabric defect image segmentation based on the visual attention mechanism of the wavelet domain [J].
Guan, Shengqi ;
Gao, Zhaoyuan .
TEXTILE RESEARCH JOURNAL, 2014, 84 (10) :1018-1033
[5]   Identification of twill grey fabric defects using DC suppressed Fourier power spectrum sum features [J].
Jayashree, V. ;
Subbaraman, Shaila .
TEXTILE RESEARCH JOURNAL, 2012, 82 (14) :1485-1497
[6]   Supervised defect detection on textile fabrics via optimal Gabor filter [J].
Jing, Junfeng ;
Yang, Panpan ;
Li, Pengfei ;
Kang, Xuejuan .
JOURNAL OF INDUSTRIAL TEXTILES, 2014, 44 (01) :40-57
[7]   Bottom-Up and Top-Down Attention: Different Processes and Overlapping Neural Systems [J].
Katsuki, Fumi ;
Constantinidis, Christos .
NEUROSCIENTIST, 2014, 20 (05) :509-521
[8]   Computer-vision-based fabric defect detection: A survey [J].
Kumar, Ajay .
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2008, 55 (01) :348-363
[9]   Familiarity based unified visual attention model for fast and robust object recognition [J].
Lee, Seungjin ;
Kim, Kwanho ;
Kim, Joo-Young ;
Kim, Minsu ;
Yoo, Hoi-Jun .
PATTERN RECOGNITION, 2010, 43 (03) :1116-1128
[10]   A computational model of vision attention for inspection of surface quality in production line [J].
Li, Guohui ;
Shi, Jinfang ;
Luo, Hongsen ;
Tang, Miangang .
MACHINE VISION AND APPLICATIONS, 2013, 24 (04) :835-844