A flexible visual inspection system based on neural networks Export

@article{citeulike:4117544, abstract = {In this work, we propose a neural networks-based machine vision system, which is intended to act as a reconfigurable inspection tool, for use in manufacturing environments. The processing engine of the system is a second-order neural network, which extracts geometric features invariant to translation and rotation. A major issue with the use of higher-order neural networks is the combinatorial explosion of the higher-order terms, which is addressed here with the use of the alternative image representation strategy of coarse coding. We developed a genetic algorithms tool, which allows the automated determination of the optimal number of hidden units in the neural networks architecture. The inspection system is tested in two application areas, namely inspection of axisymmetric components and classification of rivets. Numerous tests are carried out to evaluate the robustness of the proposed system to complex noise sources.}, author = {Liatsis, P. and Goulermas, J. Y. and Zeng and Milonidis, E.}, citeulike-article-id = {4117544}, citeulike-linkout-0 = {http://dx.doi.org/10.1080/00207720802630719}, citeulike-linkout-1 = {http://www.ingentaconnect.com/content/tandf/tsys/2009/00000040/00000002/art00007}, doi = {10.1080/00207720802630719}, issn = {0020-7721}, journal = {International Journal of Systems Science}, keywords = {computer\_vision, defect\_detection, genetic\_algorithm, neural\_network}, month = {February}, number = {2}, pages = {173--186}, posted-at = {2009-11-12 05:44:17}, priority = {2}, publisher = {Taylor and Francis Ltd}, title = {A flexible visual inspection system based on neural networks}, url = {http://dx.doi.org/10.1080/00207720802630719}, volume = {40}, year = {2009} }

TY - JOUR ID - citeulike:4117544 L3 - citeulike-article-id:4117544 N2 - In this work, we propose a neural networks-based machine vision system, which is intended to act as a reconfigurable inspection tool, for use in manufacturing environments. The processing engine of the system is a second-order neural network, which extracts geometric features invariant to translation and rotation. A major issue with the use of higher-order neural networks is the combinatorial explosion of the higher-order terms, which is addressed here with the use of the alternative image representation strategy of coarse coding. We developed a genetic algorithms tool, which allows the automated determination of the optimal number of hidden units in the neural networks architecture. The inspection system is tested in two application areas, namely inspection of axisymmetric components and classification of rivets. Numerous tests are carried out to evaluate the robustness of the proposed system to complex noise sources. IS - 2 JF - International Journal of Systems Science SN - 0020-7721 EP - 186 TI - A flexible visual inspection system based on neural networks PB - Taylor and Francis Ltd VL - 40 SP - 173 KW - computer_vision KW - defect_detection KW - genetic_algorithm KW - neural_network AU - Liatsis, P AU - Goulermas, JY AU - Zeng AU - Milonidis, E PY - 2009/02// UR - http://dx.doi.org/10.1080/00207720802630719 ER -