Improving the industrial classification of cork stoppers by using image processing and Neuro-Fuzzy computing

This paper presents a solution to a problem existing in the cork industry: cork stopper/disk classification according to their quality using a visual inspection system. Cork is a natural and heterogeneous (remarkable variability among different samples, being impossible to find two samples with the same morphological distribution in its defects) material; therefore, its automatic classification (seven quality classes exist) is very difficult. The solution proposed in this paper evaluates the following procedures: quality discriminatory features extraction and classifiers analysis. Each procedure focused on the study of aspects that could influence cork quality. Experiments show that the best results are obtained by system specific features: cork area occupied by defects (after thresholding), size of the biggest defect within the cork area (morphological operations), and the Laws TEMs E5L5TR, E5E5TR, S5S5TR, W5W5TR, all working on a Neuro-Fuzzy classifier. In conclusion, the results of this study represent an important contribution to improve quality control in the cork industry.

[1]  Robert M. Hodgson,et al.  Texture Measures for Carpet Wear Assessment , 1988, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  See-Kiong Ng,et al.  TNFIS: Tree-based neural fuzzy inference system , 2008, 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence).

[3]  E. Mizutani,et al.  Neuro-Fuzzy and Soft Computing-A Computational Approach to Learning and Machine Intelligence [Book Review] , 1997, IEEE Transactions on Automatic Control.

[4]  Kostas Karpouzis,et al.  A Neuro-fuzzy Approach to User Attention Recognition , 2008, ICANN.

[5]  Noureddine Zerhouni,et al.  Adaptive Neuro-Fuzzy Inference System for mid term prognostic error stabilization. , 2008 .

[6]  J.L. Lima,et al.  A modular approach to real-time cork classification using image processing , 2005, 2005 IEEE Conference on Emerging Technologies and Factory Automation.

[7]  Azriel Rosenfeld,et al.  Histogram concavity analysis as an aid in threshold selection , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[8]  Wen-Hsiang Tsai,et al.  Moment-preserving thresolding: A new approach , 1985, Comput. Vis. Graph. Image Process..

[9]  P.K Sahoo,et al.  A survey of thresholding techniques , 1988, Comput. Vis. Graph. Image Process..

[10]  ScienceDirect.  Nuclear instruments & methods in physics research , 1983 .

[11]  J. R. Gonzalez-Adrados,et al.  Quality grading of cork planks with classification models based on defect characterisation , 2000, Holz als Roh- und Werkstoff.

[12]  Hafiz Adnan Habib,et al.  Modified Laws Energy Descriptor for Inspection of Ceramic Tiles , 2004 .

[13]  Milan Sonka,et al.  Image processing analysis and machine vision [2nd ed.] , 1999 .

[14]  Kenneth I. Laws,et al.  Rapid Texture Identification , 1980, Optics & Photonics.

[15]  Cheng-Jian Lin,et al.  Classification and medical diagnosis using wavelet-based fuzzy neural networks , 2008 .

[16]  Milan Sonka,et al.  Image Processing, Analysis and Machine Vision , 1993, Springer US.

[17]  Brendon J. Woodford,et al.  A wavelet-based neuro-fuzzy system for data mining small image sets , 2004, ACSW.

[18]  Manuel A. Fortes.  Cork and corks , 1993 .

[19]  V. Gandhi,et al.  Image classification based on textural features usingArtificial Neural Network (ANN) , 2004 .

[20]  C. Chow,et al.  Automatic boundary detection of the left ventricle from cineangiograms. , 1972, Computers and biomedical research, an international journal.

[21]  Cordelia Schmid,et al.  Constructing models for content-based image retrieval , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[22]  Bruce A. Maxwell,et al.  Texture Edge Detection Using the Compass Operator , 2003, BMVC.

[23]  Helena Pereira,et al.  Decision Rules for Computer-Vision Quality Classification of Wine Natural Cork Stoppers , 2006, American Journal of Enology and Viticulture.

[24]  K. Benmahammed,et al.  Application of Artificial Neuro-Fuzzy Logic Inference System for Predicting the Microbiological Pollution in Fresh Water , 2008 .

[25]  Andrew Zisserman,et al.  A Statistical Approach to Texture Classification from Single Images , 2005, International Journal of Computer Vision.

[26]  Rocha,et al.  Application of an Electronic Aroma Sensing System to Cork Stopper Quality Control. , 1998, Journal of agricultural and food chemistry.

[27]  H. Pereira,et al.  Yield and quality in the production of cork stoppers , 1994, Holz als Roh- und Werkstoff.

[28]  Arief Wijaya,et al.  Soft Classification and Assessment of Kalman Filter Neural Network for Complex Landcover of Tropical Rainforests , 2008, IGARSS 2008 - 2008 IEEE International Geoscience and Remote Sensing Symposium.

[29]  Thierry Pun,et al.  A new method for grey-level picture thresholding using the entropy of the histogram , 1980 .

[30]  P. Corona,et al.  Site quality evaluation by classification tree: an application to cork quality in Sardinia , 2005, European Journal of Forest Research.

[31]  Thierry Pun,et al.  Entropic thresholding, a new approach , 1981 .

[32]  Yung-Chang Chen,et al.  Texture features for classification of ultrasonic liver images , 1992, IEEE Trans. Medical Imaging.

[33]  Manoj Kumar Tiwari,et al.  Prediction of flow stress for carbon steels using recurrent self-organizing neuro fuzzy networks , 2007, Expert Syst. Appl..

[34]  Andrew K. C. Wong,et al.  A new method for gray-level picture thresholding using the entropy of the histogram , 1985, Comput. Vis. Graph. Image Process..

[35]  Roberto Cesareo,et al.  Cork quality estimation by using Compton tomography , 2002 .

[36]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[37]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[38]  Linda G. Shapiro,et al.  Computer Vision , 2001 .

[39]  J. Francisco Duque-Carrillo,et al.  Cork quality classification system using a unified image processing and fuzzy-neural network methodology , 1997, IEEE Trans. Neural Networks.