Abstract
Considerable research efforts in computer vision applied to food quality evaluation have been developed in the last years; however, they have been concentrated on using or developing tailored methods based on visual features that are able to solve a specific task. Nevertheless, today’s computer capabilities are giving us new ways to solve complex computer vision problems. In particular, a new paradigm on machine learning techniques has emerged posing the task of recognizing visual patterns as a search problem based on training data and a hypothesis space composed by visual features and suitable classifiers. Furthermore, now we are able to extract, process, and test in the same time more image features and classifiers than before. Thus, we propose a general framework that designs a computer vision system automatically, i.e., it finds—without human interaction—the features and the classifiers for a given application avoiding the classical trial and error framework commonly used by human designers. The key idea of the proposed framework is to select—automatically—from a large set of features and a bank of classifiers those features and classifiers that achieve the highest performance. We tested our framework on eight different food quality evaluation problems yielding a classification performance of 95 % or more in every case. The proposed framework was implemented as a Matlab Toolbox available for noncommercial purposes.
Similar content being viewed by others
Notes
This problem is known in the literature as full model selection (Escalante et al. 2009).
A previous version of this paper can be found in Mery and Soto (2008) where preliminary results are presented.
In our framework, other methods were implemented, however, their performance and their computational time were not satisfactory in our experiments. The other methods are: Forward Orthogonal Search (Wei and Billings 2007), Least Square Estimation (Mao 2005), Combination with Principal Components, (Duda et al. 2001), Future Selection based in Mutual Information (Peng 2005).
In our framework, other methods were implemented; however, their performance and their computational time were not satisfactory in our experiments. The other methods are minimal distance (Duda et al. 2001), quadratic discriminat analysis (Hastie et al. 2001; Webb 2005), boosting and AdaBoost (Polikar 2006; Viola and Jones 2004), and probabilistic neural networks (MathWorks 2009; Duda et al. 2001).
The number of folders v can be another number, for instance, 5- or 20-fold cross-validation estimates very similar performances. In our experiments, we use 10-fold cross-validation because it has become the standard method in practical terms (Witten and Frank 2005).
In order to convert RGB images into L*a*b*, we use a methodology based on a calibration step with known color charts (Leon et al. 2006).
No L*a*b* information was available.
References
Aguilera, J., Cipriano, A., Eraña, M., Lillo, I., Mery, D., Soto, A. (2007). Computer vision for quality control in Latin American food industry, a case study. In Int. conf. on computer vision (ICCV2007): workshop on computer vision applications for developing countries (pp. 1–8).
Bishop, C. (2005). Neural networks for pattern recognition. London: Oxford University Press.
Bishop, C.M. (2006). Pattern recognition and machine learning. New York: Springer.
Chellappa, R., & Bagdazian, R. (1984). Fourier coding of image boundaries. IEEE Transactions on Pattern Analysis and Machine Intelligence, PAMI-6(1), 102–105.
Cheng, H., Jiang, X., Sun, Y., Wang, J. (2001). Color image segmentation: advances and prospects. Pattern Recognition, 34(12), 2259–2281. ISSN 0031-3203.
Dalal, N., & Triggs, B. (2005). Histograms of oriented gradients for human detection. In Conference on computer vision and pattern recognition (CVPR2005) (Vol. 1, pp. 886–893).
Danielsson, P.-E. (1978). A new shape factor. Computer Graphics and Image Processing, 7, 292–299.
Davies, E. (2000). Image processing for the food industry. Singapore: World Scientific.
Diaz, R., Gil, L., Serrano, C., Blasco, M., Moltó, E., Blasco, J. (2004). Comparison of three algorithms in the classification of table olives by means of computer vision. Journal of Food Engineering, 61(1), 101–107.
Duda, R., Hart, P., Stork, D. (2001). Pattern classification (2nd ed.). New York: Wiley.
Escalante, H., Montes, M., Sucar, L. (2009). Particle swarm model selection. The Journal of Machine Learning Research, 10, 405–440.
Fitzgibbon, A., Pilu, M., Fisher, R. (1999). Direct least square fitting ellipses. IEEE Transactions on Pattern Analysis and Machine Intelligence, 21(5), 476–480.
Flusser, J., & Suk, T. (1993). Pattern recognition by affine moment invariants. Pattern Recognition, 26(1), 167–174.
Gonzalez, R., & Woods, R. (2008). Digital image processing (3rd ed.). Upper Saddle River: Prentice-Hall.
Gupta, L., & Srinath, M.D. (1987). Contour sequence moments for the classification of closed planar shapes. Pattern Recognition, 20(3), 267–272.
Haff, R., & Slaughter, D. (2004). Real-time X-ray inspection of wheat for infestation by the granary weevil, sitophilus granarius (l.). Transactions of the American Society of Agricultural Engineers, 47, 531–537.
Haff, R., & Toyofuku, N. (2008). X-ray detection of defects and contaminants in the food industry. Sensing and Instrumentation for Food Quality and Safety, 2(4), 262–273.
Haralick, R. (1979). Statistical and structural approaches to texture. Proceedings of IEEE, 67(5), 786–804.
Hastie, T., Tibshirani, R., Friedman, J. (2001). The elements of statistical learning: Data mining, inference, and prediction (corrected ed.). New York: Springer.
Hu, M.-K. (1962). Visual pattern recognition by moment invariants. IRE Transactions on Information Theory, IT(8), 179–187.
Inen, M.P., Pietikäinen, M., Hadid, A., Zhao, G., Ahonen, T. (2011). Computer vision using local binary patterns (Vol. 40). London: Springer.
Irudayaraj, J., & Reh, C. (eds.) (2008). Nondestructive testing for food quality. Ames: IFT Press.
Jain, A., Duin, R., Mao, J. (2000). Statistical pattern recognition: a review. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(1), 4–37.
Jiang, J., Chang, H., Wu, K., Ouyang, C., Yang, M., Yang, E., Chen, T., Lin, T. (2008). An adaptive image segmentation algorithm for X-ray quarantine inspection of selected fruits. Computers and Electronics in Agriculture, 60, 190–200.
Kohavi, R. (1995). A study of cross-validation and bootstrap for accuracy estimation and model selection. In International joint conference on artificial intelligence (Vol. 14, pp. 1137–1145).
Kumar, A., & Pang, G. (2002). Defect detection in textured materials using gabor filters. IEEE Transactions on Industry Applications, 38(2), 425–440.
Kwon, J., Lee, J., Kim, W. (2008). Real-time detection of foreign objects using X-ray imaging for dry food manufacturing line. In Proceedings of IEEE international symposium on consumer electronics (ISCE 2008) (pp. 1–4). doi:10.1109/ISCE.2008.4559552.
Leemans, V., & Destain, M.F. (2004). A real-time grading method of apples based on features extracted from defects. Journal of Food Engineering, 61(1), 83–89.
Leiva, G., Mondragón, G., Mery, D., Aguilera, J. (2011). The automatic sorting using image processing improves postharvest blueberries storage quality. In Proceedings of international congress on engineering and food.
Leon, K., Mery, D., Pedreschi, F., Leon, J. (2006). Color measurement in l*a*b* units from rgb digital images. Food Research International, 39(10), 1084–1091.
Mao, K. (2005). Identifying critical variables of principal components for unsupervised feature selection. IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, 35(2), 339–344.
Marsland, S. (2009). Machine learning: an algorithmic perspective. London: Chapman & Hall.
MathWorks (2003). Image processing toolbox for use with MATLAB: user’s guide. The MathWorks Inc.
MathWorks (2007). Matlab toolbox of bioinformatics: user’s guide. Mathworks Inc.
MathWorks (2009). Neural network toolbox for use with MATLAB: user’s guide. The MathWorks Inc.
Mery, D. (2011). BALU: a toolbox Matlab for computer vision, pattern recognition and image processing. http://dmery.ing.puc.cl/index.php/balu.
Mery, D., & Filbert, D. (2002). Classification of potential defects in automated inspection of aluminium castings using statistical pattern recognition. In 8th European conference on non-destructive testing (ECNDT 2002), Barcelona, 17–21 June 2002 (pp. 1–10).
Mery, D., & Pedreschi, F. (2005). Segmentation of colour food images using a robust algorithm. Journal of Food Engineering, 66(3), 353–360.
Mery, D., & Soto, A. (2008). Features: the more the better. In ISCGAV’08: Proceedings of the 8th conference on signal processing, computational geometry and artificial vision (pp. 46–51). Wisconsin: Stevens Point.
Mery, D., Chanona-Pérez, J., Soto, A., Aguilera, J., Cipriano, A., Veléz-Rivera, N., Arzate-Vázque, I., Gutiérrez-López, G. (2010). Quality classification of corn tortillas using computer vision. Journal of Food Engineering, 101(4), 357–364.
Mery, D., Lillo, I., Loebel, H., Riffo, V., Soto, A., Cipriano, A., Aguilera, J. (2011). Automated fish bone detection using X-ray imaging. Journal of Food Engineering, 105(2011), 485–492.
Mitchell, T. (1997). Machine learning. Boston: McGraw-Hill.
Mu, Y., Yan, S., Liu, Y., Huang, T., Zhou, B. (2008). Discriminative local binary patterns for human detection in personal album. In IEEE conference on computer vision and pattern recognition (CVPR 2008) (pp. 1–8)
Nixon, M., & Aguado, A. (2008). Feature extraction and image processing (2nd ed.). New York: Academic.
Ogawa, Y., Kondo, N., Shibusawa, S. (2003). Inside quality evaluation of fruit by X-ray image. In 2003 IEEE/ASME international conference on advanced intelligent mechatronics, 2003. AIM 2003. Proceedings (Vol. 2, pp. 1360–1365).
Ojala, T., Pietikainen, M., Maenpaa, T. (2002). Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(7), 971–987.
Pedreschi, F., Mery, D., Mendoza, F., Aguilera, J. (2004). Classification of potato chips using pattern recognition. Journal of Food Science, 69(6), E264–E270.
Persoon, E., & Fu, K., (1977). Shape discrimination using Fourier descriptors. IEEE Transactions on Systems, Man, and Cybernetics, SMC-7(3), 170–179.
Polikar, H., Long, F., Ding, C. (2005). Criteria of max-dependency, max-relevance and min-redundancy. IEEE Transactions on Pattern Analysis and Machine Intelligence, 27(8), 1226-1238.
Polikar, R. (2006). Ensemble based systems in decision making. IEEE Circuits and Systems Magazine, 3rd Quarter, 21–45.
Quevedo, R., Mendoza, F., Aguilera, J., Chanona, J., Gutiérrez-López, G. (2008). Determination of senescent spotting in banana (Musa cavendish) using fractal texture fourier image. Journal of Food Engineering, 84(4), 509–515.
Shawe-Taylor, J., & Cristianini, N. (2004). Kernel methods for pattern analysis. Cambridge: Cambridge University Press.
Sun, D. (2000). Inspecting pizza topping percentage and distribution by a computer vision method. Journal of Food Engineering, 44(4), 245–249.
Sun, D.-W. (ed.) (2008). Computer vision technology for food quality evaluation. New York: Academic.
Szeliski, R. (2011). Computer vision: algorithms and applications. New York: Springer.
Tan, J. (2004). Meat quality evaluation by computer vision. Journal of Food Engineering, 61(1), 27–35.
Viola, P., & Jones, M. (2004). Robust real-time object detection. International Journal of Computer Vision, 57(2), 137–154.
Webb, A. (2005). Statistical pattern recognition. England: Wiley.
Wei, H.-L., & Billings, S. (2007). Feature subset selection and ranking for data dimensionality reduction. IEEE Transactions on Pattern Analysis and Machine Intelligence, 29(1), 162–166, Jan.
Witten, I., & Frank, E., (2005). Data mining: practical machine learning tools and techniques (2nd. ed.). San Mateo, CA: Morgan Kaufmann.
Zahn, C., & Roskies, R., (1971). Fourier descriptors for plane closed curves. IEEE Transactions on Computers, C-21(3), 269–281.
Acknowledgements
This work was supported partially by grant no. R0308LAC003 from LACCIR Virtual Institute and grant no. 1070031 from FONDECYT, Chile. Blueberry images were provided by G. Leiva, G. Mondragón, and C. Arrieta from Pontificia Universidad Catolica de Chile. Corn Tortilla images were provided by J.J. Chanona-Pérez, N. Veléz-Rivera, I. Arzate-Vázquez, and G.F. Gutiérrez-López from Instituto Politécnico Nacional de México.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Mery, D., Pedreschi, F. & Soto, A. Automated Design of a Computer Vision System for Visual Food Quality Evaluation. Food Bioprocess Technol 6, 2093–2108 (2013). https://doi.org/10.1007/s11947-012-0934-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11947-012-0934-2