Defect detection in textured materials using optimized filters
IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics) - Tập 32 Số 5 - Trang 553-570 - 2002
Tóm tắt
The problem of automated defect detection in textured materials is investigated. A new approach for defect detection using linear FIR filters with optimized energy separation is proposed. The performance of different feature separation criteria with reference to fabric defects has been evaluated. The issues relating to the design of optimal filters for supervised and unsupervised web inspection are addressed. A general web inspection system based on the optimal filters is proposed. The experiments on this new approach have yielded excellent results. The low computational requirement confirms the usefulness of the approach for industrial inspection.
Từ khóa
#Finite impulse response filter #Inspection #Gabor filters #IIR filters #Fabrics #Information filtering #Information filters #Quality assurance #Textile industry #ProductionTài liệu tham khảo
Özdemir, 1996, markov random fields and karhunen-loève transforms for defect inspection of textile products, Proc IEEE Conf Emerging Technologies and Factory Automation EFTA 96, 2, 697
10.1109/IAS.2001.955418
10.1117/1.601751
campbell, 1997, Flaw detection in woven textiles using space-dependent fourier transform
10.1117/1.601692
10.1117/1.600663
10.1117/1.601054
vachtsevanos, 1998, Method and apparatus for analyzing an image to detect and identify defects
10.1117/1.1327837
10.1109/28.993164
mead, 1978, Method for Automatic Fabric Inspection
10.1109/28.871274
10.1016/0143-8166(95)00044-O
10.1109/28.806035
10.1109/ISIE.1999.796918
10.1016/0167-8655(84)90044-8
10.1109/ICPR.1992.201654
ade, 1984, comparison of various filter sets for defect detection in textiles, Proc 7th Int Conf Pattern Recognit, 1, 428
10.1109/IECON.1993.339359
10.1142/S0218001496000554
10.1016/S0262-8856(99)00009-8
10.1177/004051759606600710
10.1016/0031-3203(91)90143-S
10.1109/21.105080
10.1007/BF01213639
randen, 1996, optimal filtering for unsupervised texture feature extraction, Proc SPIE Conf Visual Communications and Image Process, 430
randen, 1997, optimal texture filter design using feature extraction modeling, Working papers from H⊘ gskolen i Stavanger no 27
papoulis, 1991, Probability Random Variables and Stochastic Processes 3rd ed
10.1016/S0262-8856(00)00041-X
cohen, 1991, automated inspection of textile fabrics using textural models, IEEE Trans Pattern Anal Machine Intelll, 803, 10.1109/34.85670
10.1177/004051750007000902
10.1177/004051759506501109
lane, 1998, Textile fabric inspection system
10.1109/ICSMC.1998.727546
10.1109/ICSMC.1998.727529
10.1109/34.3870
10.1109/TPAMI.1983.4767446
10.1177/004051759506500301
10.1109/TENCON.1997.647318
10.1016/S0169-7552(98)00211-6
kumar, 2001, Automated defect detection in textured materials
10.1016/0957-4158(95)00004-O
10.1007/978-1-4471-3201-1_23
10.1177/004051759506500101
10.1117/12.164868
fukunaga, 1990, Statistical Pattern Recognition 2nd ed
10.1117/12.171200
10.1016/0165-1684(86)90095-2
mahalanobis, 1994, correlation filters for texture recognition and applications to terrain-delimitation in wide-area surveillance, Proc Int Conf Acousti Speech Signal Processing ICASSP 94, 5, 153
10.1109/ICIP.1995.529724
10.1109/83.753744
10.1117/12.223998
10.1109/ROBOT.1997.620007
10.1364/AO.33.002173
campbell, 1996, Linear flaw detection in woven textiles using model-based clustering