A method for classifying oranges based on image processing and neural networks

Subject Areas :

Hassan  Rashidi ¹ (Faculty of Statistics, Mathematical and Computer Sciences, Allameh Tabataba’i University, Tehran, Iran)
Faride  Esmaili ² (Young Researchers and Elite Club, Qazvin Branch, Islamic Azad University, Qazvin, Iran)
Mostafa  Khojastehnazhand ³ (Department of Mechanical Engineering, Faculty of Engineering, University of Bonab, Bonab, Iran)

Received: 2021-12-12 Accepted : 2022-03-01 Published : 2022-03-01

Keywords: defects, machine vision, Image processing /, Orange /, Co-occurrence matrix /,

Abstract :

In recent days, there have been many recommendations on social media about eating healthy fruits to strengthen the immune system and corona resistance. Therefore, it is very important to identify spoiled fruits at this time when human society is concerned about coronavirus and the human body needs healthy fruits in case of this disease. This paper proposes a method to identify the type of defects found in orange fruits. We used a machine vision system to capture sample images, which includes a charge-coupled device camera, black box, lighting system, and personal computer. The citrus fruits are classified into eight classes, including Wind scar, Stem-end breakdown, Snail bites, Thrips scar, Scale injury, Medfly, Rings, and Calyx, depending on the type and model of the defects. In the proposed method, classification by the neural network with the help of co-occurrence matrix for four angles θ=0°, 45°, 90°, and 135°, were extracted to identify various defects and 24 features related to the areas with defect in citrus. For the final classification of defects in citrus, after evaluating many classification tools from various tools available, Feed-forward Back Propagation Neural Network (FFBPNN) is used. The result of the neural network classifier was obtained with the help of the co-occurrence matrix by taking four angles (horizontal, right diagonal, vertical, and left diagonal) with an accuracy of 89.65%. The evaluation shows acceptable results compared with similar studies. It is a reliable method in the food classification industry with reasonable accuracy.

References:

1. Zhang B, Huang W, Li J, Zhao C, Fan SH, Wu J, Liu CH. Principles, developments and applications of computer vision for external quality inspection of fruits and vegetables: A review. Science Direct on Food Research International. 2014;62(1):326-43.


2. Zhao JW, Ouyang Q, Chen QS, Wang JH. Detection of bruise on pear by hyperspectral imaging sensor with different classification algorithms. Sensor Letters. 2010;8(4):570-6.


3. Baranowski P, Mazurek W, Wozniak J, Majewska U. Detection of early bruises in apples using hyperspectral data and thermal imaging. Journal of Food Engineering. 2012;110(3):345-55.


4. Haff RP, Saranwong S, Thanapase W, Janhiran A, Kasemsumran S, Kawano S. Automatic image analysis and spot classification for detection of fruit fly infestation in hyperspectral images of mangoes. Postharvest Biology and Technology. 2013;86, 23-8.


5. Hu MH, Dong QL, Liu BL, Malakar PK. The potential of double K-means clustering for banana image segmentation. Journal of Food Process Engineering. 2014;37(1):10-8.


6. Blasco J, Aleixos N, Gomez-Sanch J, Molto E. Recognition and classification of external skin damage in citrus fruits using multispectral data and morphological feature. Biosystems Engineering. 2009;103(2):137-45.


7. Gomez-Sanchis J, Martin-Guerrero JD, Soria-Olivas E, Martinez-Sober M, Magdalena-Benedito R., Blasco J. Detecting rottenness caused by Penicillium genus fungi in citrus fruits using machine learning techniques. Expert Systems with Applications. 2012;39(1):780-5.


8. Lopez-Garcia F, Andreu-Garcia G, Blasco J, Aleixos N, Valiente JM. Automatic detection of skin defects in citrus fruits using a multivariate image analysis approach. Computers and Electronics in Agriculture. 2010;71(2):189-97.


9. Li JB, Rao X, Ying YB. Detection of common defects on oranges using hyperspectral reflectance imaging, Computers and Electronics in Agriculture. 2011;78(1):38-48.


10. Blasco J, Aleixos N, Molto E. Machine vision system for automatic quality grading of fruit. Biosystems Engineering. 2003;85(4):415-23.


11. Cuevas FJ, Pereira-Caro G, Moreno-Rojas JM, Muñoz-Redondo JM, Ruiz-Moreno MJ. Assessment of premium organic orange juices authenticity using HPLC-HR-MS and HS-SPME-GC-MS combining data fusion and chemometrics. Food Control. 2017;82,203-11.


12. Thendral R, Suhasini A. Automated skin defect identification system for orange fruit grading based on genetic algorithm. Current Science. 2017;112(8):1704-11.


13. López-Froilán R, Hernández-Ledesma B, Cámara M, Pérez-Rodríguez ML. Evaluation of the antioxidant potential of mixed fruit-based beverages: A new insight on the Folin-Ciocalteu method. Food Analytical Methods. 2018;11(10):2897-906.


14. Mavi MF, Husin Z, Badlishah AR, Farook RSM, Tan WK. Mango ripeness classification system using hybrid technique. Indonesian Journal of Electrical Engineering and Computer Science. 2019;14(2):859-68.


15. Li Y, Feng X, Liu Y, Han X. Apple quality identification and classification by image processing based on convolutional neural networks. Scientific Report. 2021;11,16618.


16. Renzetti FR, Zortea L. Use of a gray level co-occurrence matrix to characterize duplex stainless steel phases microstructure. Fratturaed Integrità Strutturale. 2011;16(1):43-51.


17. Haralick RM, Shanmugam K, Dinstein IH. Textural features for image classification. IEEE Transactions on Systems, Man and Cybernetics. 1973;6,610-21.


18. Soh LK, Tsatsoulis C. Texture analysis of SAR sea ice imagery using gray level co-occurrence matrices. IEEE Transactions On geoscience and Remote Sensing. 1999;37(2):780-2.


19. Ileana I, Rotar C, Incze A. The Optimization of feed-forward neural networks structure using genetic algorithms. International Conference on Theory and applications of Mathematics and Informatics, Thessaloniki, Greece. 2004. pp. 223-4.


20. Lopez J, Cobos M, Aguilera E. Computer-based detection and classification of flaws in citrus fruits. Science Direct Neural Compute & Applic, 2011;975-81.


21. Kasinathan T, Uyyala SR. Machine learning ensemble with image processing for pest identification and classification in field crops. Neural Computing and Applications. 2021;33,7491-504.


22. Mohamed AR, El Masry GM, Radwan SA, ElGamal RA. Development of a real-time machine vision prototype to detect external defects in some agricultural products. Journal of Soil Sciences and Agricultural Engineering. 2021;12(5):317-25.


23. Behera SK, Rath AK, Sethy PK. Fruit recognition using support vector machine based on deep features. Karbala International Journal of Modern Science. 2020;6(2):1-13.