Classification of Robust and Rotten Apples by Deep Learning Algorithm

In the study, it is aimed to classify the apples as rotten and robust by using the deep learning algorithm of the apple images taken from the CAPA database. In the proposed model, the processing steps are image reading, preprocessing and classification of apples, respectively. In the image reading stage, images taken from the image database were used. The applied deep learning architecture consists of introduction, convolutional, activation, pooling, memorization, full connection and conclusion layers. The data used in this architecture are divided into two as 80% training and 20% test data. Four different wavelength, 16 kinds of image combinations were used for the training and testing of the system. At the classification stage, a success rate of 91.25% was achieved in detecting rotten and robust apples. As a result, it is predicted that the proposed model can be used in the fruit processing industry to automatically classify rotten and robust apples.

Sağlam ve Çürük Elmaların Derin Öğrenme Algoritması ile Sınıflandırılması

Yapılan çalışmada, CAPA veri tabanından alınan elma görüntülerinin derin öğrenme algoritması kullanılarak, elmaların çürük ve sağlam olarak sınıflandırılması amaçlanmıştır. Önerilen modelde işlem adımları sırasıyla görüntü okuma, önişleme ve elmaların sınıflandırılmasıdır. Görüntü okuma aşamasında, görüntü veri tabanından alınan görüntüler kullanılmıştır. Uygulanan derin öğrenme mimarisi giriş, evrişimsel, aktivasyon, havuzlama, ezberleme, tam bağlantı ve sonuçlandırma katmanlarından oluşmaktadır. Bu mimaride kullanılan veriler, %80 eğitim ve %20 test verisi olmak üzere ikiye ayrılmıştır. Sistemin eğitim ve test işlemleri için dört farklı dalga boyunda, 16 çeşit görüntü kombinasyonu kullanılmıştır. Sınıflandırma aşamasında, çürük ve sağlam elmaların tespit edilmesinde %91.25 başarı oranına ulaşılmıştır. Sonuç olarak, önerilen modelin meyve işleme sanayisinde çürük ve sağlam elmaların otomatik olarak sınıflandırılmasında kullanılabileceği ön görülmektedir.

PDF

___

[1] H. Kurt, Ş. Ö. Keşkek, T. Çil, and A. Canataroğlu, “Meme kanserli hastalarda tamamlayıcı/alternatif tedavi kullanımı,” Türk Onkol. Derg., vol. 28, no. 1, pp. 10–15, 2013.

[2] C. A. Perussello, Z. Zhang, A. Marzocchella, and B. K. Tiwari, “Valorization of apple pomace by extraction of valuable compounds,” Compr. Rev. Food Sci. Food Saf., vol. 16, no. 5, pp. 776– 796, 2017.

[3] O. Cömert, M. Hekim, and K. Adem, “Faster R-CNN Kullanarak Elmalarda Çürük Tespiti,” Uluslararası Mühendislik Araştırma ve Geliştirme Derg., vol. 11, no. 1, pp. 335–341.

[4] V. Leemans, H. Magein, and M.-F. Destain, “On-line fruit grading according to their external quality using machine vision,” Biosyst. Eng., vol. 83, no. 4, pp. 397–404, 2002.

[5] M. M. Sofu, O. Er, M. C. Kayacan, and B. Cetişli, “Elmaların görüntü işleme yöntemi ile sınıflandırılması ve leke tespiti,” Gıda Teknol. Elektron. Derg., vol. 8, no. 1, pp. 12–25, 2013.

[6] Y. Lu and R. Lu, “Detection of surface and subsurface defects of apples using structuredillumination reflectance imaging with machine learning algorithms,” Trans. ASABE, vol. 61, no. 6, pp. 1831–1842, 2018.

[7] R. Siddiqi, “Automated apple defect detection using state-of-the-art object detection techniques,” SN Appl. Sci., vol. 1, no. 11, p. 1345, 2019.

[8] Y. Yu, S. A. Velastin, and F. Yin, “Automatic grading of apples based on multi-features and weighted K-means clustering algorithm,” Inf. Process. Agric., 2019.

[9] O. Kleynen, V. Leemans, and M.-F. Destain, “Development of a multi-spectral vision system for the detection of defects on apples,” Journal of Food Engineering, vol. 69, no. 1, pp. 41–49, 2005.

[10] B. Zhang et al., “Principles, developments and applications of computer vision for external quality inspection of fruits and vegetables: A review,” Food Res. Int., vol. 62, pp. 326–343, 2014.

[11] S. Cubero, W. S. Lee, N. Aleixos, F. Albert, and J. Blasco, “Automated systems based on machine vision for inspecting citrus fruits from the field to postharvest—a review,” Food Bioprocess Technol., vol. 9, no. 10, pp. 1623–1639, 2016.

[12] A. Folch-Fortuny, J. M. Prats-Montalbán, S. Cubero, J. Blasco, and A. Ferrer, “VIS/NIR hyperspectral imaging and N-way PLS-DA models for detection of decay lesions in citrus fruits,” Chemom. Intell. Lab. Syst., vol. 156, pp. 241–248, 2016.

[13] X. Zhu and G. Li, “Rapid detection and visualization of slight bruise on apples using hyperspectral imaging,” Int. J. Food Prop., vol. 22, no. 1, pp. 1709–1719, 2019.

[14] Z. Du, X. Zeng, X. Li, X. Ding, J. Cao, and W. Jiang, “Recent advances in imaging techniques for bruise detection in fruits and vegetables,” Trends Food Sci. Technol., 2020.

[15] X. Zeng, Y. Miao, S. Ubaid, X. Gao, and S. Zhuang, “Detection and classification of bruises of pears based on thermal images,” Postharvest Biol. Technol., vol. 161, p. 111090, 2020.

[16] M. Zhang, Y. Jiang, C. Li, and F. Yang, “Fully convolutional networks for blueberry bruising and calyx segmentation using hyperspectral transmittance imaging,” Biosyst. Eng., vol. 192, pp. 159–175, 2020.

[17] Y. LeCun et al., “Backpropagation applied to handwritten zip code recognition,” Neural Comput., vol. 1, no. 4, pp. 541–551, 1989.

[18] R. P. Lippmann, “Review of neural networks for speech recognition,” Neural Comput., vol. 1, no. 1, pp. 1–38, 1989.

[19] B. Yuan, “Efficient hardware architecture of softmax layer in deep neural network,” in 2016 29th IEEE International System-on-Chip Conference (SOCC), 2016, pp. 323–326.

[20] A. Kamilaris and F. X. Prenafeta-Boldú, “Deep learning in agriculture: A survey,” Comput. Electron. Agric., vol. 147, pp. 70–90, 2018.

[21] J. Wan et al., “Deep learning for content-based image retrieval: A comprehensive study,” in Proceedings of the 22nd ACM international conference on Multimedia, 2014, pp. 157–166.

[22] M. I. Razzak, S. Naz, and A. Zaib, “Deep learning for medical image processing: Overview, challenges and the future,” in Classification in BioApps, Springer, 2018, pp. 323–350.

[23] C. Tian, Y. Xu, L. Fei, and K. Yan, “Deep Learning for Image Denoising: A Survey,” Int. Conf. Genet. Evol. Comput., pp. 563–572, 2018.

[24] V. Leemans and M.-F. Destain, “A real-time grading method of apples based on features extracted from defects,” J. Food Eng., vol. 61, no. 1, pp. 83–89, 2004.

[25] J. Xing and J. De Baerdemaeker, “Bruise detection on ‘Jonagold’apples using hyperspectral imaging,” Postharvest Biol. Technol., vol. 37, no. 2, pp. 152–162, 2005.

[26] D. Unay and B. Gosselin, “Automatic defect segmentation of ‘Jonagold’apples on multi-spectral images: A comparative study,” Postharvest Biol. Technol., vol. 42, no. 3, pp. 271–279, 2006.

[27] D. Unay, B. Gosselin, O. Kleynen, V. Leemans, M.-F. Destain, and O. Debeir, “Automatic grading of Bi-colored apples by multispectral machine vision,” Comput. Electron. Agric., vol. 75, no. 1, pp. 204–212, 2011.

[28] S. H. Mohana and C. J. Prabhakar, “Stem-calyx recognition of an apple using shape descriptors,” arXiv Prepr. arXiv1501.01083, 2015.

[29] S. R. Dubey and A. S. Jalal, “Apple disease classification using color, texture and shape features from images,” Signal, Image Video Process., vol. 10, no. 5, pp. 819–826, 2016.

[30] Y. Lu and R. Lu, “Histogram-based automatic thresholding for bruise detection of apples by structured-illumination reflectance imaging,” Biosyst. Eng., vol. 160, pp. 30–41, 2017.

[31] S. Zhang, X. Wu, S. Zhang, Q. Cheng, and Z. Tan, “An effective method to inspect and classify the bruising degree of apples based on the optical properties,” Postharvest Biol. Technol., vol. 127, pp. 44–52, 2017.

[32] “Gömülü kamera sistemleri”, [Online]. https://www.matrix-vision.com/smart-cam-compactapplication-camera.html [Erişim tarihi: 21.05.2020.]