Recognition of Natural and Non-Natural Defects Presented in Ophthalmic Lenses

This paper is concerned with the design of a classification system based on artificial neural networks to distinguish between natural and non-natural cosmetic defects found in ophthalmic lenses. Natural cosmetic defects are related to small cotton fabrics, and non-natural defects are formed during the fabrication process. A set of geometric, morphology and topologic features are defined in order to represent these defects. The recognition problem of theses defects is faced with feedforward and SOM artificial neural networks paradigms. The performance of the feedforward and SOM networks turned to be similar, 92.35% of correct classification. The performance of these neural networks is acceptable compared against the performance of a human inspector considering that a human inspector reaches a performance between 85% and 90%. Besides, the ANN approach is completely free of changes in its decision, contrary to a human inspector that can change his/her mind due to subjective influences.

[1]  John C. Russ,et al.  The Image Processing Handbook , 2015 .

[2]  H. Sánchez.  Optimización de una medida de semejanza para objetos tridimensionales a partir de invariantes y transformaciones , 2009 .

[3]  Ari Visa,et al.  Fourier-Based Object Description in Defect Image Retrieval , 2006, Machine Vision and Applications.

[4]  M.I.M. Chacon,et al.  Cosmetic defect classification found in ophthalmic lenses using artificial neural networks , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[5]  Slobodan Ribaric,et al.  A biometric identification system based on eigenpalm and eigenfinger features , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Robert F. Murphy,et al.  Object type recognition for automated analysis of protein subcellular location , 2005, IEEE Transactions on Image Processing.

[7]  R. Murphy,et al.  Objective Clustering of Proteins Based on Subcellular Location Patterns , 2005, Journal of biomedicine & biotechnology.

[8]  Alfonso Padilla-Vivanco,et al.  Digital image reconstruction using Zernike moments , 2004, SPIE Remote Sensing.

[9]  Andrew G. Dempster,et al.  Attributed skeleton graphs using mathematical morphology , 2001 .

[10]  A. Soini,et al.  Machine vision technology take-up in industrial applications , 2001, ISPA 2001. Proceedings of the 2nd International Symposium on Image and Signal Processing and Analysis. In conjunction with 23rd International Conference on Information Technology Interfaces (IEEE Cat..

[11]  Hideo Saito,et al.  The evaluating system of human skin surface condition by image processing , 2000, Smc 2000 conference proceedings. 2000 ieee international conference on systems, man and cybernetics. 'cybernetics evolving to systems, humans, organizations, and their complex interactions' (cat. no.0.

[12]  Paul L. Rosin.  Measuring shape: ellipticity, rectangularity, and triangularity , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[13]  Chi Chung Ko,et al.  Using moment invariants and HMM in facial expression recognition , 2000, 4th IEEE Southwest Symposium on Image Analysis and Interpretation.

[14]  Ming-Kuei Hu,et al.  Visual pattern recognition by moment invariants , 1962, IRE Trans. Inf. Theory.

[15]  Dieter Filbert,et al.  CLASSIFICATION OF POTENTIAL DEFECTS IN THE AUTOMATIC INSPECTION OF ALUMINIUM CASTINGS USING STATISTICAL PATTERN RECOGNITION , 2002 .

[16]  P. W. Hawkes,et al.  Digital image processing , 1980, Nature.