A system for real-time fabric inspection and industrial decision

ABSTRACT

This work presents an application of software engineering to fabric inspection. An inspection system has been developed for textile industries that aims automatic failure detection. Such as wood, paper and steel industries, this environment has particular characteristics in which surface defect detection is used for quality control. This system combines concept from software engineering and decision support. Detection of defects within the inspected texture is performed in a first step acquiring images by CCD cameras, then extracting texture features and, finally by classifiers being trained a priori on database of defective and non-defective samples. The extracted data depend on the type of method selected for image analysis. The used types are based on segmentation or fractal dimension. Two usual segmentation techniques were adapted and improved. A new algorithm was developed to calculate efficiently fractal dimension of textures. Experiments show the accuracy and applicability of the proposed techniques for a real factory environment.

REFERENCES

• 1: Berztiss, A T. Requirements engineering, in Handbook of Software Engineering and Knowledge Engineering, vol. 1: Fundamentals, Edited by S K Chang, USA, 2002.
• 2: C. Chang, The structure of quality information systems in a computer integrated manufacturing environment, Computers and Industrial Engineering, v.15 n.1, p.338-343, December 1988 [doi>10.1016/0360-8352(88)90108-8]
• 3: Chetverikov, D. Pattern regularity as a visual key, Image and Vision Computing, vol. 18(2000), 975-985.
• 4: Chin, R T and Harlow, C A. Automated visual inspection: a survey, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PAMI-4 ( 6 -1982), 557-573.
• 5: Aura Conci , Claudia Belmiro Proença, A fractal image analysis systems for fabric inspection based on a box-counting method, Computer Networks and ISDN Systems, v.30 n.20-21, p.1887-1895, Nov. 1998 [doi>10.1016/S0169-7552(98)00211-6]
• 6: Conci, A and Proença, C B. A Comparison between Image-processing Approaches on Textile Inspection, Journal of the Textile Institute - ISSN 0400-5000, Manchester, Ref.: 76-98, vol. 91 Part 1- Fibber Science and Textile Technology, No. 2 (2000), 317-323.
• 7: Conci, A and Proença, C B. A Computer Vision Approach for Textile Inspection, Textile Research Journal, published by Textile Research Institute, Princeton, New Jersey - ISSN 0040-5175, Vol. 70 No. 4, April (2000), 347-350.
• 8: Conci, A and Proença, C B. Researches to automatic failure detection. Revista Brasileira de Ciências Mecânicas - RBCM- ISSN 0100-7386, Ed. ABCM, vol. XXI, n 3 (1999), 493-508 (in Portuguese).
• 9: Gangepain, J and Roques-Carmes, C. Fractal approach to two dimensional and three dimensional surface roughness, Wear, vol. 109(1986) 119-126.
• 10: Gevers, T. and Smeulders, A. W. M. Colour Based Object Recognition, Pattern Recognition, 32 ( 1999) 457-464.
• 11: Rafael C. Gonzalez , Richard E. Woods, Digital Image Processing, Addison-Wesley Longman Publishing Co., Inc., Boston, MA, 1992
• 12: J. M. Keller , S. Chen , R. M. Crownover, Texture description and segmentation through fractal geometry, Computer Vision, Graphics, and Image Processing, v.45 n.2, p.150-166, February 1, 1989 [doi>10.1016/0734-189X(89)90130-8]
• 13: Latif-Amet, A., Ertüzün, A. and Erçil, A. An efficient method for texture defect detection: sub-band domain co-occurrence matrices, Image and Vision Computing, vol. 18, (2000) 543-553.
• 14: Mandelbrot, B. The Fractals Geometry of Nature, Freeman, CA. 1982.
• 15: Mirenkov, N., Vazhenin, A., Yoshioka, R., Ebihara, T., Hirotomi, T. and Mirenkova, T. Self-explanatory components: a new programming paradigm, Int. Journal of Software Eng. and Knowledge Eng., vol. 11, No. 1,(2000) 5-36.
• 16: Peleg, S, Naor, J, Hartley R and Avnir D. Multiple resolution texture analysis and classification, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PAMI-6 (4 - 1984) 518-523.
• 17: Pentland A P. Fractal based description of natural scenes, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. PAMI-6 ( 4 - 1984) 661-674.
• 18: John C. Russ, The image processing handbook (2nd ed.), CRC Press, Inc., Boca Raton, FL, 1995
• 19: Sarkar, N and Chaudhuri, B. An efficient differential box-counting approach to compute fractal dimension of image, IEEE Transactions on Systems, Man and Cybernetics, vol. 24(1 - 1984) 115-120.
• 20: Sethi, A K and Suresh, P S. Flexibility in manufacturing: a survey, International Journal of Flexible Manufacturing Systems, vol. 2 (1990) 289-328.
• 21: Shah, M, Lin, L and Nagi, R. A production order-driven AGV control model with object-oriented implementation, J. of Computer Integrated Manufacturing Systems, vol. 10 (1 - 1997) 35-48.
• 22: Talavage, J and Hannam, R G. Flexible Manufacturing Systems in Practice: Applications, Design and Simulation, Marcel-Dekker, New York, 1988.
• 23: Watt, A. and Policarpo, F. 3D Games: Real-time Rendering and Software Technology, vol. 1, (1st. Ed.), Addison-Wesley, UK, 2001.

INDEX TERMS

Primary Classification:
  G. Mathematics of Computing
  G.1 NUMERICAL ANALYSIS
      G.1.0 General

Additional Classification:
  H. Information Systems
  H.5 INFORMATION INTERFACES AND PRESENTATION (I.7)
      H.5.2 User Interfaces (D.2.2, H.1.2, I.3.6)

  I. Computing Methodologies
  I.3 COMPUTER GRAPHICS
      I.3.6 Methodology and Techniques
  I.4 IMAGE PROCESSING AND COMPUTER VISION
      I.4.0 General

  J. Computer Applications
  J.6 COMPUTER-AIDED ENGINEERING

General Terms:
Algorithms, Design, Economics, Experimentation, Management, Measurement, Performance, Reliability, Verification

Keywords:
decision support systems, industrial application, real-time quality control