Abstract
Combining knowledge-based processing with image processing is a key issue in the future of the visual inspection of complex patterns such as offset prints. Often the class of the defect determines the state of the process, which must known for eliminating the cause of the defect. We describe the architecture of such a complex knowledge-based inspection system. The system has been used for defect recognition and misprint diagnosis in offset printing, but it is flexible enough for other applications. The system is based on a set of general and powerful tools for the knowledge interpretation of sensor signals. An object-oriented concept and task-dependent algorithms for efficient image processing are implemented. The paper concentrates on four points: integration of the system in the offset printing process, a description of the system architecture, knowledge acquisition, and implementation results.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Bartlett SL, Besl PJ, Cole CL, Jain R, Mukherjee D, Skifstad KD (1988) Automatic solder joint inspection. IEEE Patt Anal Machine Intell 10:31–43
Boose JH, Shema DB, Bradshaw JM (1989) Recent progress in Aquinas: a knowledge-acquisition workbench. Knowl acquisition 1:185–214
Butler KA, Corter JE (1986) Use of psychometric tools for knowledge. Addison-Wesley, Reading, Mass
Dom BE, Brecher VH, Bonner R, Batchelder JS, Jaffe RS (1988) The P300: a system for automatic patterned wafer inspection. Machine Vision Appl 4:205–221
Erenyi I, Pongracz J (1991) Quality control in the textile industry via machine vision. Microprocess microprogram 32:807–814
Hedengren K (1989) Methodology for automatic image-based inspection of industrial objects. In: Sanz JLC (ed) Advances in machine vision. Springer, Berlin Heidelberg New York, pp 100–130
Kehoe A, Parker GA (1991) An IKB defect classification system for automated industrial radiographic inspection. IEEE Expert Syst 8:149–157
Klapproth U, Perner P, Böhme B (1991) An expert system for the diagnosis of misprints in offset printing (in German). Messen Steuern Regeln 34:116–120
May V (1991) SWD-Expert, Manual, Leipzig University of Technology, Leipzig
Niemann H (1990) Pattern analysis and understanding, 2nd edn. Springer, Berlin Heidelberg New York pp 161–163
Perner P (1993) Application of knowledge-based image inspection system for diagnosis of misprints in offset printing (Lecture Notes in Computer Science) Proceedings of the 6th International Conference on Computer Analysis and Image Processing 1993, vol 719. Springer Verlag, Berlin Heidelberg New York pp 738–749
Perner P (1993) A repertory grid-based knowledge-acquisition tool for visual inspection tasks. Internal Report, Leipzig University of Technology, Leipzig
Perner P, Böhme B (1990) A knowledge-based diagnosis system for opto-electronic quality control (in German). Messen Steuern Regeln 33:410–420
Perner P, Haselbauer W, Matz G (1990) A real-time image preprocessing unit on the basis of signal processor TMS 320 C20. vol 5. Proceedings of the 6th International Conference on Process Automation of Leipzig University of Technology, Leipzig, pp 61–65
Petkovic D, Hinkle EB (1987) A rule-based system for verifying engineering specifications in industrial visual inspection applications. IEEE Patt Anal Machine Intell 9:306–311
Polygraph Werner Lamberz (1987) Technical Report of the Department of Science and Technology, VEB Polygraph Werner Lamberz, Leipzig
Silver WM, Schott J-P (1990) Practical golden template comparison. Technical Report, June 6, 1990, COGNEX Vision for Industry, Needham, Mass.
Simon H (1975) Automatic image analysis in medicine and biology (in German). Steinkopff, Dresden, pp 100–110
Uebel W, Friedrich A, Hoffmann H (1989) Bestimmung der Farbanteilemehrfarbiger Druckvorlagen mit bildanalytischen Methoden. Messen Steuern Regeln 32:5
Woschni HG, Lehmer R (1990) Subpixel resolution with CCD sensors. Proceedings of the 6th International Conference on Process Automation of Leipzig University of Technology, Leipzig, vol 5, pp 38–43
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Perner, P. A knowledge-based image-inspection system for automatic defect recognition, classification, and process diagnosis. Machine Vis. Apps. 7, 135–147 (1994). https://doi.org/10.1007/BF01211659
Issue Date:
DOI: https://doi.org/10.1007/BF01211659