We present a novel online inspection method for manufacturing processes that automatically adapts to variations in part and environmental properties. This method is based on a developmental learning architecture comprising a procedure that focuses attention to apparently defective regions, a recognition method that performs automatic feature derivation based on a set of training images and hierarchical classification, and an action step that controls attention and further decision processes. The method adapts to variations incrementally by updating rather than recreating the training information. Also, the method is capable of inspecting and training simultaneously. Addressing new inspection tasks requires neither re-programming and compatibility tests, nor quantitative knowledge about the image set, from a human developer. Instead, automatic or manual training of the inspection system according to simple guidelines is applied. These attributes allow the method to improve online performance with minimal ramp-up time. Our system performed inspection of three applications with low error rate and fast recognition, confirming its suitability for general-purpose, real-time, online inspection.
Skip Nav Destination
e-mail: gabramov@engine.umich.edu
e-mail: weng@cse.msu.edu
e-mail: dutta@engine.umich.edu
Article navigation
November 2005
Technical Papers
Adaptive Part Inspection Through Developmental Vision
Gil Abramovich,
Gil Abramovich
Department of Mechanical Engineering,
e-mail: gabramov@engine.umich.edu
The University of Michigan
, Ann Arbor, MI 48109
Search for other works by this author on:
Juyang Weng,
Juyang Weng
Department of Computer Science and Engineering,
e-mail: weng@cse.msu.edu
Michigan State University
, East Lansing, MI 48824
Search for other works by this author on:
Debasish Dutta
Debasish Dutta
Department of Mechanical Engineering,
e-mail: dutta@engine.umich.edu
The University of Michigan
, Ann Arbor, MI 48109
Search for other works by this author on:
Gil Abramovich
Department of Mechanical Engineering,
The University of Michigan
, Ann Arbor, MI 48109e-mail: gabramov@engine.umich.edu
Juyang Weng
Department of Computer Science and Engineering,
Michigan State University
, East Lansing, MI 48824e-mail: weng@cse.msu.edu
Debasish Dutta
Department of Mechanical Engineering,
The University of Michigan
, Ann Arbor, MI 48109e-mail: dutta@engine.umich.edu
J. Manuf. Sci. Eng. Nov 2005, 127(4): 846-856 (11 pages)
Published Online: March 8, 2005
Article history
Received:
November 21, 2003
Revised:
March 8, 2005
Citation
Abramovich, G., Weng, J., and Dutta, D. (March 8, 2005). "Adaptive Part Inspection Through Developmental Vision." ASME. J. Manuf. Sci. Eng. November 2005; 127(4): 846–856. https://doi.org/10.1115/1.2039103
Download citation file:
Get Email Alerts
Cited By
Related Articles
Recognition of User-Defined Turning Features for Mill/Turn Parts
J. Comput. Inf. Sci. Eng (September,2007)
On-Line Seam Detection in Rolling Processes Using Snake Projection and Discrete Wavelet Transform
J. Manuf. Sci. Eng (October,2007)
Pattern Recognition for Automatic Machinery Fault Diagnosis
J. Vib. Acoust (April,2004)
Quality and Inspection of Machining Operations: CMM Integration to the Machine Tool
J. Manuf. Sci. Eng (October,2009)
Related Chapters
Introduction
Marketing of Engineering Consultancy Services: A Global Perspective
Inspection and Maintenance of Ageing Concrete Oil and Gas Structures on the Norwegian Continental Shelf
Ageing and Life Extension of Offshore Facilities
Computer Aided Manufacturing (CAM)
Computer Aided Design and Manufacturing