An approach for improve the recognition of defects in coffee beans using retinex algorithms

This paper describes the development of a system for evaluating the quality of coffee focused on the pre-processing of digital images using an algorithm based on the retinex theory called multi-scale retinex with color restoration (MSRCR). A dataset of images of coffee beans are collected and others techniques for image enhancement are compared, then a color gray-level coocurrence matrix (CGLCM) technique is used for features extraction and a Support Vector Machine (SVM) is used to evaluate results with a set of prepared data, these results shows a good visual quality and better accuracy in classification for MSRCR techniques compared with others, finally conclusions and future works are presented.

[1]  Chun-Liang Chien,et al.  COLOR IMAGE ENHANCEMENT WITH EXACT HSI COLOR MODEL , 2011 .

[2]  Zia-ur Rahman,et al.  Properties and performance of a center/surround retinex , 1997, IEEE Trans. Image Process..

[3]  Rabab Kreidieh Ward,et al.  Fast Image/Video Contrast Enhancement Based on Weighted Thresholded Histogram Equalization , 2007, IEEE Transactions on Consumer Electronics.

[4]  Constantine Kotropoulos,et al.  Color image histogram equalization by absolute discounting back-off , 2007, Comput. Vis. Image Underst..

[5]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[6]  John D. Austin,et al.  Adaptive histogram equalization and its variations , 1987 .

[7]  Karel J. Zuiderveld,et al.  Contrast Limited Adaptive Histogram Equalization , 1994, Graphics Gems.

[8]  E H Land,et al.  Recent advances in retinex theory and some implications for cortical computations: color vision and the natural image. , 1983, Proceedings of the National Academy of Sciences of the United States of America.

[9]  Charles Elkan,et al.  Evaluating Classifiers , 2006 .

[10]  Faridah Faridah,et al.  Coffee Bean Grade Determination Based on Image Parameter , 2011 .

[11]  Robin N. Strickland,et al.  Digital Color Image Enhancement Based On The Saturation Component , 1987 .

[12]  Jean-Michel Morel,et al.  A PDE Formalization of Retinex Theory , 2010, IEEE Transactions on Image Processing.

[13]  Ioannis Pitas,et al.  Multichannel techniques in color image enhancement and modeling , 1996, IEEE Trans. Image Process..

[14]  Rahman Zia-ur,et al.  A Multiscale Retinex for Color Rendition and Dynamic Range Compression , 1996 .

[15]  Aichi Chien,et al.  An L1-based variational model for Retinex theory and its application to medical images , 2011, CVPR 2011.

[16]  E. Land,et al.  Lightness and retinex theory. , 1971, Journal of the Optical Society of America.

[17]  E. Land.  Recent advances in retinex theory , 1986, Vision Research.

[18]  Somasundaram Karuppanagounder,et al.  Bi-Level Weighted Histogram Equalization for Scalable Brightness Preservation and Contrast Enhancement for Images , 2013, Int. Arab J. Inf. Technol..

[19]  KimYeong-Taeg.  Contrast enhancement using brightness preserving bi-histogram equalization , 1997 .

[20]  Habtamu Minassie.  Image Analysis for Ethiopian Coffee Classification , 2008 .

[21]  Toby P. Breckon,et al.  Fundamentals of Digital Image Processing: A Practical Approach with Examples in Matlab , 2011 .

[22]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[23]  P. Batt.  Expanding the quality concept to satisfy consumer demand , 2007 .

[24]  Flavio Augusto Prieto Ortiz,et al.  SEGMENTACIÓN DE FRUTOS DE CAFÉ MEDIANTE MÉTODOS DE CRECIMIENTO DE REGIONES , 2006 .

[25]  S. Osher,et al.  A TV Bregman iterative model of Retinex theory , 2012 .

[26]  C. A. Murthy,et al.  Hue-preserving color image enhancement without gamut problem , 2003, IEEE Trans. Image Process..

[27]  Zia-ur Rahman,et al.  Multi-scale retinex for color image enhancement , 1996, Proceedings of 3rd IEEE International Conference on Image Processing.

[28]  R. Hudec,et al.  Novel Method for Color Textures Features Extraction Based on GLCM , 2007 .

[29]  Robert A. Hummel,et al.  Image Enhancement by Histogram transformation , 1975 .

[30]  Panos Trahanias,et al.  Color image enhancement through 3-D histogram equalization , 1992, Proceedings., 11th IAPR International Conference on Pattern Recognition. Vol. III. Conference C: Image, Speech and Signal Analysis,.

[31]  Michael Elad,et al.  A Variational Framework for Retinex , 2002, IS&T/SPIE Electronic Imaging.

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

[33]  Yeong-Taeg Kim,et al.  Contrast enhancement using brightness preserving bi-histogram equalization , 1997 .

[34]  F. A. P. Ortíz,et al.  CARACTERIZACIÓN DE CAFÉ CEREZA EMPLEANDO TÉCNICAS DE VISIÓN ARTIFICIAL , 2007 .

[35]  E. Land.  The retinex theory of color vision. , 1977, Scientific American.