38 8 38th Annual Conference of CSQ & 8th NQMS MCP IE
120 1. [1] [4] 1 2 3 2. Chetverikov Lerch[8,12] LeaVis CAD Limas-Serafim[6,7] (multi-resolution pyramids) 2 n 2 n 2 2 (texture) (calf leather) (veins)
121 (scares) Lovergine [18] (leather patch) (fold) Branca [9] 10 15 45 (oriented texture) (lash) (cut) (gored) (wart) (eczema) (stretch mark) (not uniform color) 10 10 Hoang Nachimuthu[14,15] (thresholding value) Kittler Illingworht (minimum error thresholding method)[ 17] CAD Gerard Bertrand[13] 96%( ) Yeh Perng Alapuranen and Westman[5] RGB Parikh[19] Schettini[21] Horaud[16] [2]
122 3. 3.1 1 1
123 1 [4] R G B [19] 1 2 2 1 3.2 2 4. 4.1 48 3
124 1. 1mm( ). 1mm... ( ) 1mm( ) 1mm.. ( ) ( ) ( ) (, ) 10 2 (%) 14 2.87 0.19 15 15 13 15 15 1 10 13 19 7 19 13 1 10 13 2.75 0.15 1.74 0.10 1.16 0.05 (%)
125 6 6 7 (Learn rate) 0.03 (Momentum) 0.8 4 2
126 3 10000 ( ) 1 1 6 0.1833 1 3 8 0.1580 1 6 11 0.1443 1 12 15 0.1452 2 6 11 0.1472 2 8 12 0.1497 2 10 14 0.1482 2 12 15 0.1483 2 14 17 0.1477 3 6 14 0.2186 4 ( ) 51 0.0637 72 0.0751 63 0.1381 71 0.1734 5 RMS ErrorCorrelation 0.000006 0.001232 0.999996 0.005438 0.999811 0.033474 0.991391 0.03 1000000 5 5 0.0006% 0.12% 0.54% 3.34%
127 4.2 1 Visual Basic 1 30 Excel 170 6 6 1 30 2.16% 0.43% 3 3 Visual Basic 50 1000 4 50 1000 0.054% 4.3 50 1000 0.06% 100%
128 6 (%) (%) (%) 1 23 0 0 6 0 0 4 0 0 2 16 0 0 20 0 0 49 0 0 3 50 3 6 56 0 0 40 0 0 4 51 1 1.96 41 0 0 45 0 0 5 75 2 2.67 45 0 0 57 0 0 6 79 0 0 98 1 1.02 64 0 0 7 61 2 3.28 143 0 0 127 0 0 8 117 5 4.27 114 1 0.88 122 0 0 9 129 4 3.1 104 1 0.96 119 0 0 10 142 3 2.11 137 2 1.46 181 0 0 12 161 2 1.24 194 1 0.52 166 0 0 14 195 3 1.54 188 1 0.53 173 0 0 16 190 2 1.05 191 0 0 205 0 0 18 173 5 2.89 213 2 0.94 231 0 0 20 273 3 1.1 274 2 0.73 193 0 0 22 335 6 1.79 322 0 0 325 0 0 24 327 8 2.45 283 0 0 300 0 0 26 324 7 2.16 312 1 0.32 264 0 0 28 362 10 2.76 336 2 0.6 499 0 0 30 433 12 2.77 344 2 0.58 400 0 0 2.1574 0.4266 0 3 4
129 5. 1. 2. 3. 4. 5. ( ) 6. (NSC90-2218-E-035-004) 1. 2. 17 6 593 601 89 3. B1-1 4. António F. Limas-Serafim, Natural images segmentation for patterns recognition using edges pyramids and its application to the leather defects, Proceedings IECON. IEEE, 1357-1360(1993). 5. António F. Limas-Serafim, Multi-resolution pyramids for segmentation of natural images based on auto-regressive models: Application to calf leather classification, Proceedings IECON. IEEE, 1842-1847(1991).
130 6. Attila Lerch and Dmitry Chetverikov Knowledge-based Line-correction rules in a machine-vision system for the leather industry, Engineering Applications of Artificial Intelligence, 4(6), 433-438(1991). 7. Branca A., M. Tafuri, G. Attolico and A. Distante, Automated system for detection and classification of leather defects, Optical Engineering, 35(12), 3485-3497(1996). 8. Chung Yeh and Der-Baau Perng, A reference standard of defect compensation for leather transaction, The International Journal of Integrated Manufacturing Systems. submitted March 28 2002. 9. Chung Yeh and Der-Baau Perng Establishing demerit count reference for leather hides classification and grading standard, The International Journal of Advanced Manufacturing Technology, 18:731-738 (NSC89-2213-E-035-022) (2001). 10. Dmitry Chetverikov and Attila Lerch Prototype machine vision system for segmentation of hide images, International Journal of Imaging Systems and Technology, 4,46-50(1992). 11. Gerard YAHIAOUI and Bertrand BOROCCO, An Industrial Application of Neural Networks to Natural Textures Classification International Workshop on Artifical Neural Network, IWA NN 93, Sitges, Spain, 1993. 12. Hoang K. and A. Nachimuthu, Image processing techniques for leather hide ranking on the footwear industry, Machine Vision and Applications, 9, 119-29(1996). 13. Hoang K., W. Wen, A. Nachimuthu and X. L. Jiang, Achieving automation in leather surface inspection, Computers in Industry, 34, 43-54, (1997). 14. Kittler J. and J. Illingworth. Minimum error thresholding, Pattern Recognition 19(l), 41-47, (1986). 15. Lovergine F.P., A. Branca, G. Attolico and A. Distante Leather inspection by oriented texture analysis with a morphological approach, Proceedings, International Conference on Image Processing IEEE Comput. Soc. Part 2, 669-671(1997).