Hyperspectral LCTF-based system for classification of decay in mandarins caused by Penicillium digitatum and Penicillium italicum using the most relevant bands and non-linear classifiers

Postharvest Biology and Technology

Volumn 82, Issue , 2013, Pages 76-86

  Gomez Sanchis J ^a   Blasco, J ^b   Soria Olivas, E ^a   Lorente, D ^b   Escandell Montero, P ^a   Martinez Martinez J M ^a   Martinez Sober M ^a   Aleixos, N ^c  

^a UNIVERSITY OF VALENCIA   (Spain)

^b INSTITUTO VALENCIANO DE INVESTIGACIONES AGRARIAS IVIA   (Spain)

^c UNIVERSITAT POLITÈCNICA DE VALÈNCIA   (Spain)

Author keywords

Decay; Feature selection; Fruit inspection; Hyperspectral imaging; Image analysis; Machine vision; Mandarins; Non linear classifiers

Indexed keywords

CITRUS; FUNGI; PENICILLIUM; PENICILLIUM DIGITATUM; PENICILLIUM ITALICUM;

EID: 84875797943     PISSN: 09255214     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.postharvbio.2013.02.011     Document Type: Article

References (43)

1. Abe N., Kudo M., Toyama J., Shimbo M. A divergence criterion for classifier-independent feature selection. Lecture notes in computer science. Adv. Pattern Recogn. 2000, 1876:668-676.
2. Aleixos N., Blasco J., Navarrón F., Moltó Multispectral inspection of citrus in real-time using machine vision and digital signal processors. Comput. Elect. Agric. 2002, 33(2):121-137.
3. Arivazhagan S., Ganesan L., Priyal S. Texture classification using Gabor wavelets based rotation invariant features. Pattern Recogn. Lett. 2006, 27(16):1976-1982.
4. Blanc, P., Blasco, J., Moltó, E., Gómez-Sanchis, J., and Cubero, S. (2007). Sistema para la selección selectiva automática de cítricos afectados por podredumbre. Ref. P200700514 Ofi{ligature}cina Española de Patentes y Marcas. 27/02/2007. Patent Issued.
5. Blasco J., Aleixos N., Moltó E. Computer vision detection of peel defects in citrus by means of a region oriented segmentation algorithm. J. Food Eng. 2007, 81(3):535-543.
6. Blasco J., Aleixos N., Gómez-Sanchis J., Moltó E. Citrus sorting by identification of the most common defects using multispectral computer vision. J. Food Eng. 2007, 83(3):384-393.
7. Blum A., Langley P. Selection of relevant features and examples in machine learning. Artif. Intell. 1998, 97:245-271.
8. Cubero S., Aleixos N., Moltó E., Gómez-Sanchis J., Blasco J. Advances in machine vision applications for automatic inspection and quality evaluation of fruits and vegetables. Food Bioprocess Technol. 2011, 4(4):487-504.
9. Eckert J., Brown G., Usall J., Viñas I. Evaluation of postharvest treatments for citrus fruits. Method. Eval. Pest. Control Plant Pathog. 1986, 92-97.
10. ElMasry G., Wang N., Vigneault C. Detecting chilling injury in Red delicious apple using hyperspectral imaging and neural networks. Postharvest Biol. Technol. 2009, 52:1-8.
11. Friedman J. An overview of predictive learning and function approximation. From Statistics to Neural Networks, Proc. NATO/ASI Workshop 1994, 1-61.
12. Gómez-Chova L., Calpe J., Soria E., Camps-Valls G., Martín J., Moreno J. CART- based feature selection of hyperspectral images for crop cover classification. IEEE Int. Conf. Image Process. (ICIP2003) 2003, 2. pages III-589-92, Spain.
13. Gómez-Chova, L., 2008. Cloud screening algorithm for MERIS and CHRIS multispectral sensors, University of Valencia Spain, Ph.D. Thesis.
14. Gómez-Sanchis J., Gómez-Chova L., Aleixos N., Camps-Valls G., Montesino-Herrero C., Moltó E., Blasco J. Hyperspectral system for early detection of rottenness caused by Penicillium digitatum in mandarins. J. Food Eng. 2008, 89(1):80-86.
15. Gómez-Sanchis J., Camps-Valls G., Moltó E., Gómez-Chova L., Aleixos N., Blasco J. Segmentation of hyperspectral images for the detection of rotten mandarins. Lecture notes in computer science. Image Anal. Recogn. 2008, 5112:1071-1080.
16. Gómez-Sanchis J., Moltó E., Camps-Valls G., Gómez-Chova L., Aleixos N., Blasco J. Automatic correction of the effects of the light source on spherical objects. An application to the analysis of hyperspectral images of citrus fruits. J. Food Eng. 2008, 85(2):191-200.
17. Gómez-Sanchis J., Blasco J., Moltó J., Camps-Valls G. Hyperspectral detection of citrus damage with Mahalanobis Kernel classifier. IEE Electron. Lett. 2007, 43(20):1082-1084.
18. Gómez-Sanchis J., Martín-Guerrero J.D., Soria-Olivas E., Martínez-Sober M., Magdalena-Benedito R., Blasco J. Detecting rottenness caused by Penicillium in citrus fruits using machine learning techniques. Expert Sys. Appl. 2012, 39(1):780-785.
19. Ham J., Chen C., Crawford M., Ghosh J. Investigation of the random forest framework for classifi{ligature}cation of hyperspectral data. IEEE Trans. Geosci. Remote Sens. 2005, 43(3):492-501.
20. Kleynen O., Leemans V., Destain M. Development of a multi-spectral vision system for the detection of defects on apples. J. Food Eng. 2005, 69(1):41-49.
21. Kohavi R., John G. Wrappers for features subset selection. Int. J. Digital Libr. 1997, 1:108-121.
22. Leemans V., Magein H., Destain M. On-line fruit grading according to their external quality using machine vision. Biosyst. Eng. 2002, 83(4):397-404.
23. Li S., Liao C., Kwok J. Gene feature extraction using T-test statistics and Kernel partial least squares. Lecture notes in computer science. Neural Inf. Process. 2006, 4234:11-20.
24. Lorente, D., Aleixos, N., Gómez-Sanchis, J., Cubero, S., Blasco, J. Selection of optimal wavelengths features for the decay detection in citrus fruit using the ROC curve and neural networks. Food and Bioprocess Technology. in press. doi:10.1007/s11947-011-0737-x.
25. Lorente D., Aleixos N., Gómez-Sanchis J., Cubero S., García-Navarrete O.L., Blasco J. Recent advances and applications of hyperspectral imaging for fruit and vegetable quality assessment. Food Bioprocess Technol. 2012, 5(4):1121-1142.
26. Mäenpä T., Turtinen M., Pietikäinen M. Real-time surface inspection by texture. Real Time Imag. 2003, 9(5):289-296.
27. Mamitsuka H. Selecting features in microarray classification using ROC curves. Pattern Recogn. 2006, 39(12):2393-2404.
28. Matcher S., Cope M., Delpy D. Use of the water absorption spectrum to quantify tissue chromophore concentration changes in near-infrared spectroscopy. Phys. Med. Biol. 1994, 39:177-196.
29. Nakariyakula S., Casasent P. Fast feature selection algorithm for poultry skin tumor detection in hyperspectral data. J. Food Eng. 2009, 94(3/4):358-365.
30. Ortuño A., Báidez A., Gómez P., Arcas M., Porras I., García-Lidón P., Del Río J. Citrus paradisi and citrus sinensis flavonoids: Their influence in the defence mechanism against Penicillium digitatum. J. Roy. Stat. Soc. B 2006, 98(2):351-358.
31. Ouardighi A., Akadi A., Aboutajdine D. Feature selection on supervised classification using Wilks lambda statistic. International Symposium on Computational Intelligence and Intel Ligent Informatics ISCIII07, vol. 1 2007, 51-55.
32. Palou L., Smilanick J., Usall J., Viñaas I. Control postharvest blue and green molds of oranges by hot water, sodium carbonate, and sodium bicarbonate. Plant Dis. 2001, (85):371-376.
33. Palou L., Smilanick J.L., Droby S. Alternatives to conventional fungicides for the control of citrus postharvest green and blue moulds. Stewart Postharv. Rev. 2008, 4(2):1-16.
34. Ponsa D., López A. Feature selection based on a new formulation of the minimal redundancy-maximal-relevance criterion. Lecture notes in computer science. Pattern Recogn. Image Anal. 2007, 4477:47-54.
35. Rohrmus D. Invariant and adaptive geometrical texture features for defect detection and classification. Pattern Recogn. 2005, 38(10):1546-1559.
36. Sim J., Wright C.C. The kappa statistic in reliability studies: use, interpretation, and sample size requirements. Phys. Ther. 2005, 85:257-268.
37. Sims D., Gamon J. Estimation of vegetation water content and photosynthetic tissue area from spectral reflectance: a comparison of indices based on liquid water and chlorophyll absorption features. Remote sens. Environ. 2003, 84(4):526-537.
38. Theodoridis S., Koutroumbas K. Pattern Recognition 1999, Academic Press, Burlington, MA, USA.
39. Trias-Sanz R., Stamon G., Louchet J. Using colour, texture, and hierarchial segmentation for high-resolution remote sensing. ISPRS J. Photogramm. Remote Sens. 2008, 63(2):156-168.
40. Waheeda T., Bonnell R., Prashera S., Pauleta E. Measuring performance in precision agriculture: CART, a decision tree approach. Agric.Water Manage. 2006, 84(1/2):173-185.
41. Wallays C., Missotten B., DeBaerdemaeker J., Saeys W. Hyperspectral waveband selection for on-line measurement of grain cleanness. Biosyst. Eng. 2009, 104(1):1-7.
42. Ye X., Sakai K., Ortega-Garciano L., Asada S., Sasao A. Estimation of citrus yield from airborne hyperspectral images using a neural network model. Ecol. Model. 2006, 198(3/4):426-432.
43. Zhai Y., Thomasson J., Bogges J., Sui R. Soil texture classification with artificial neural networks operating on remote sensing data. Comput. Electron. Agric. 2006, 54(2):53-68.