Evrişimsel Sinir Ağları Kullanılarak Yumurta Kabuğu Kusurlarının Tespiti

Ticari yumurta çiftliği endüstrilerinde, kusurlu yumurtaların otomatik olarak ayrılması ekonomik ve sağlık açısından önemlidir. Günümüzde, kusurlu yumurtaların tespiti manuel olarak yapılmaktadır. Bu durum, zaman alıcı, yorucu ve karmaşık süreçler içermektedir. Tüm bu nedenlerden dolayı, yumurta yüzeyinde oluşabilecek kusurların otomatik olarak sınıflandırılması oldukça önemli bir konu haline gelmiştir. Bu amaç doğrultusunda, bu çalışmada, nesne tanıma ve sınıflandırma alanlarında yüksek performans sağlayan Evrişimsel Sinir Ağlarına (ESA) dayalı geliştirilen AlexNet, VGG16, VGG19, SqueezeNet, GoogleNet, Inceptionv3, ResNet18 ve Xception mimarileri kullanılarak yumurta kusurlarının sınıflandırılması gerçekleştirilmiştir. Bu mimarilerin performansını test etmek için kirli, kanlı, kırık ve sağlam yumurtaları içeren özgün bir veri seti inşa edilmiştir. Deneysel çalışmalar sonucunda, en yüksek doğruluk skoru VGG19 mimarisi ile %96,25 olarak elde edilmiştir. Bu sonuçlarda, ESA yöntemlerinin kusurlu yumurtaların sınıflandırılmasında yüksek başarı sağladığı gözlenmiştir.

Detection of Eggshell Defects using Convolutional Neural Networks

In commercial egg farming industries, the automatic sorting of defective eggs is economically and healthily important. Nowadays, detect of defective eggs is performed manually. This situation involves time consuming, tiring and complex processes. For all these reasons, automatic classification of defects that may occur on the egg surface has become a very important issue. For this purpose, in this study, classification of egg defects was performed using AlexNet, VGG16, VGG19, SqueezeNet, GoogleNet, Inceptionv3, ResNet18, and Xception architectures, which were developed based on Convolutional Neural Networks (CNN), which provide high performance in object recognition and classification. To test the performance of these architectures, an original data set containing dirty, bloody, cracked, and intact eggs were built. As a result of experimental studies, the highest accuracy score was obtained with VGG19 architecture as 96.25%. In these results, it was observed that ESA methods achieved high success in classifying defective eggs.

PDF

___

Abbaspour-Gilandeh Y, Azizi A. 2018. Identification of Cracks in Eggs Shell Using Computer Vision and Hough Transform. Yüzüncü Yıl Üniversitesi Tarım Bilimleri Dergisi, 28(4), 375-383.
Altuntaş Y, Cömert Z, Kocamaz AF. 2019. Identification of haploid and diploid maize seeds using convolutional neural networks and a transfer learning approach. Computers and Electronics in Agriculture, 163, 104874.
Arivazhagan S, Shebiah RN, Sudharsan H, Kannan RR, Ramesh R. 2013. External and internal defect detection of egg using machine vision. Journal of Emerging Trends in Computing and Information Sciences, 4(3), 257-262.
Başaran E, Cömert Z, Sengur A, Budak Ü, Celik Y, Toğaçar M. 2020. Normal ve Kronik Hastalıklı Orta Kulak İmgelerinin Evrişimsel Sinir Ağları Yöntemiyle Tespit Edilmesi. Türkiye Bilişim Vakfı Bilgisayar Bilimleri ve Mühendisliği Dergisi, 13(1), 1-10.
Chollet F. 2017. Xception: Deep learning with depthwise separable convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1251-1258).
Durmuş İ, Yenice E, Demirtaş ŞE. 2007. Egg abnormality. Tavukçuluk Araştırma Dergisi, 7(1), 66-71.
Guanjun B, Mimi J, Yi X, Shibo C, Qinghua Y. 2019. Cracked egg recognition based on machine vision. Computers and Electronics in Agriculture, 158, 159-166.
He K, Zhang X, Ren S, Sun J. 2016. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770-778).
Krizhevsky A, Sutskever I, Hinton GE. 2012. Imagenet classification with deep convolutional neural networks, InAdvances in neural information processing systems, 1097-1105.
Landola FN, Han S, Moskewicz MW, Ashraf K, Dally WJ, Keutzer K. 2016. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and< 0.5 MB model size. arXiv preprint arXiv:1602.07360.
Leiqing P, Kang T, Zipeng S, Jiali Y, Hongwen L. 2007. Crack detection in eggs using computer vision and BP neural network [J]. Transactions of the Chinese Society of Agricultural Engineering, 5.
Nasiri A, Omid M, Taheri-Garavand A. (2020). An automatic sorting system for unwashed eggs using deep learning. Journal of Food Engineering, 110036.
Omid M, Soltani M, Dehrouyeh MH, Mohtasebi SS, Ahmadi H. 2013. An expert egg grading system based on machine vision and artificial intelligence techniques. Journal of food engineering, 118(1), 70-77.
Öztürk N. 2014. Görüntü işleme teknikleri ile beyaz yumurtalar üzerindeki yumurta kabuğu kusurlarının algılanması, Yüksek Lisans Tez, Karadeniz Teknik Üniversitesi, Trabzon, Turkiye.
Öztürk N, Gangal A. 2014. Eggshell defects detection on white eggs using image processing techniques. In 2014 22nd Signal Processing and Communications Applications Conference (SIU) (pp. 810-813). IEEE.
Patel VC, McClendon RW, Goodrum JW. 1998. Color computer vision and artificial neural networks for the detection of defects in poultry eggs. In Artificial Intelligence for Biology and Agriculture (pp. 163-176). Springer, Dordrecht.
Simonyan K, Zisserman A. 2014. Very deep convolutional networks for large-scale image recognition, In ICLR.
Syahrir WM, Suryanti A, Ain NN. 2007. Eggs Bloodspot Detection Using Image Processing. In Second International Conference on Innovative Computing, Informatio and Control (ICICIC 2007) (pp. 424-424). IEEE.
Szegedy C. et al., 2015. Going deeper with convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1-9).
Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z. 2016. Rethinking the inception architecture for computer vision. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2818-2826).
Turkoglu M. 2019. Görüntü işleme tabanlı bitki türleri ve hastalıkları tanıma. Doktora Tezi, Fen Bilimleri Enstitüsü, İnönü Üniversitesi, Malatya, Türkiye.
Turkoglu M, Hanbay D. 2019. Plant disease and pest detection using deep learning-based features. Turkish Journal of Electrical Engineering & Computer Sciences, 27(3), 1636-1651.
Turkoglu M. 2020. COVIDetectioNet: COVID-19 diagnosis system based on X-ray images using features selected from pre-learned deep features ensemble. Applied Intelligence, 1-14.
Turkoglu M, Hanbay K, Sivrikaya IS, Hanbay D. 2020. Derin Evrişimsel Sinir Ağı Kullanılarak Kayısı Hastalıklarının Sınıflandırılması. Bitlis Eren Üniversitesi Fen Bilimleri Dergisi, 9(1), 334-345.
Wu L, Wang Q, Jie D, Wang S, Zhu Z, Xiong L. 2018. Detection of crack eggs by image processing and soft-margin support vector machine. Journal of Computational Methods in Sciences and Engineering, 18(1), 21-31.