Yumurta Kabuğu Görüntülerinde Kırık Tespiti İçin Daha Hızlı Bölgesel Tabanlı Çok Katmanlı Evrişimsel Sinir Ağları
Öz
Kırık yumurtaların otomatik olarak tespiti sağlık açısından büyük bir önem taşımaktadır. Günümüzde, kırık yumurtaların ayrıştırılması uzmanlar tarafından gözlem yoluyla yapılmaktadır. Bu işlem, yorucu olmakla birlikte zaman kaybına ve hatalı tespitlere yol açmaktadır. Bu doğrultuda, otomatik olarak yumurta yüzeyindeki kırık tespiti için Bölgesel tabanlı Evrişimsel Sinir Ağlara dayalı bir sistem tasarlanmıştır. Önerilen 16 katmanlı ESA tabanlı modelde eğitim ve test aşaması için kırık yumurta görüntülerini içeren özgün bir veri seti oluşturulmuştur. MATLAB platformu kullanılarak 107 yumurta görüntüsündeki kırık bölgeler etiketlenmiştir. Deneysel çalışmalar kapsamında, kırık bölge tespiti için önerilen model kullanılarak %95.66 ortalama kesinlik elde edilmiştir. Bu sonuçlar, önerilen bilgisayar destekli bu sistemin gıda sanayisinde otomatik olarak kırık yumurtaların ayrıştırılması amacıyla kullanılabileceğini göstermiştir.
Anahtar Kelimeler
Yumurta Kırık tespiti Daha hızlı evrişimsel sinir ağları Segmentasyon Bilgisayar destekli tespit sistemi Ortalama kesinlik
Destekleyen Kurum
Tubitak 1512 (Teknogirişim Sermayesi Desteği Programı)
Proje Numarası
2180160
Teşekkür
Bu çalışma, Tubitak 1512 (Teknogirişim Sermayesi Desteği Programı) kapsamında 2180160 nolu proje sonuçlarından hazırlanmıştır. Desteği için TUBİTAK’a teşekkür ederiz.
Kaynakça
- [1] N. Öztürk, “Görüntü işleme teknikleri ile beyaz yumurtalar üzerindeki yumurta kabuğu kusurlarının algılanması,” Yüksek Lisans Tez, Karadeniz Teknik Üniversitesi, Trabzon, Turkiye, 2014.
- [2] İ. Durmuş, E. Yenice and Ş. E. Demirtaş, “Egg abnormality,” Tavukçuluk Araştırma Dergisi, vol. 7, no. 1, pp. 66-71, 2007.
- [3] J. Priyadumkol, C. Kittichaikarn, and S. Thainimit, “Crack detection on unwashed eggs using image processing,” Journal of Food Engineering, vol. 209, pp. 76-82, 2007.
- [4] N. Öztürk and A. Gangal, “Eggshell defects detection on white eggs using image processing techniques,” In 2014 22nd Signal Processing and Communications Applications Conference (SIU), pp. 810-813, 2014.
- [5] M. Omid, M. Soltani, M. H. Dehrouyeh, S. S. Mohtasebi and H. Ahmadi, “An expert egg grading system based on machine vision and artificial intelligence techniques,” Journal of food engineering, vol. 118, no. 1, pp. 70-77, 2013.
- [6] B. Guanjun, J. Mimi, X. Yi, C. Shibo and Y. Qinghua, “Cracked egg recognition based on machine vision,” Computers and Electronics in Agriculture, vol. 158, pp. 159-166, 2019.
- [7] L. Wu, Q. Wang, D. Jie, S. Wang, Z. Zhu and L. Xiong, “Detection of crack eggs by image processing and soft-margin support vector machine,” Journal of Computational Methods in Sciences and Engineering, vol. 18, no. 1, pp. 21-31, 2018.
- [8] Y. Abbaspour-Gilandeh, and A. Azizi, “Identification of Cracks in Eggs Shell Using Computer Vision and Hough Transform,” Yüzüncü Yıl Üniversitesi Tarım Bilimleri Dergisi, vol. 28, no. 4, pp. 375-383, 2018.
- [9] J. Yang, C. Y. Xia, H. Pan, Y. Shi, and X. Y. Li, “Research of Test Model for Eggshell Crack Detection,” Advanced Materials Research. Vol. 846, Trans Tech Publications Ltd, 2014.
- [10] M. H. Abdullah, S. Nashat, S. A. Anwar and M. Z. Abdullah, “A framework for crack detection of fresh poultry eggs at visible radiation,” Computers and Electronics in Agriculture, vol. 141, pp. 81-95, 2017.
- [11] A. K. Datta, B. Botta and S. S. R. Gattam, “Damage detection on chicken eggshells using Faster R-CNN,” 2019 ASABE Annual International Meeting. American Society of Agricultural and Biological Engineers, 2019.
- [12] Q. Li, and G. Chen, “Recognition of industrial machine parts based on transfer learning with convolutional neural network,” Plos one, vol. 16, no. 1, pp. e0245735, 2021.
- [13] M. Turkoglu, “COVIDetectioNet: COVID-19 diagnosis system based on X-ray images using features selected from pre-learned deep features ensemble,” Applied Intelligence, pp. 1-14, 2020.
- [14] S. K. Khare, and V. Bajaj, “Time-frequency representation and convolutional neural network-based emotion recognition,” IEEE transactions on neural networks and learning systems, pp. 1-9, 2020.
- [15] F. Demir, M. Turkoglu, M. Aslan, and A. Sengur, “A new pyramidal concatenated CNN approach for environmental sound classification,” Applied Acoustics, vol. 170, pp. 107520, 2020.
- [16] D. Şengür and S. Siuly, “Efficient approach for EEG-based emotion recognition,” Electronics Letters, vol. 56, no. 25, pp. 1361-1364, 2020.
- [17] M. B. ER, “Akciğer Seslerinin Derin Öğrenme ile Sınıflandırılması,” Gazi Üniversitesi Fen Bilimleri Dergisi Part C: Tasarım ve Teknoloji, vol. 8, no. 4, pp. 830-844, 2020.
- [18] Y. Guo, Y. Peng and B. Zhang, “CAFR-CNN: coarse-to-fine adaptive faster R-CNN for cross-domain joint optic disc and cup segmentation,” Applied Intelligence, pp. 1-25, 2021.
- [19] S. Ren, K. He, R. Girshick and J. Sun, “Faster R-CNN: towards real-time object detection with region proposal networks,” IEEE transactions on pattern analysis and machine intelligence, vol. 39, no. 6, pp. 1137-1149, 2016.
Faster region-based multi-layer convolutional neural networks for cracked detection in eggshell images
Öz
Automatic detection of cracked eggs is of great importance in terms of health. Today, the separation of cracked eggs is done by experts through observation. This process causes time loss and erroneous detections together with tiring. In this direction, a system based on Region-based Convolutional Neural Networks has been designed for the automatic detection of cracked egg surface. A original data set containing cracked eggs images were created for the training and testing phase of the proposed 16-layer ESA-based model. Cracked regions in 107 egg images using the MATLAB platform were labeled. Within the scope of experimental studies, an average precision of 95.66% was obtained by using the proposed model for cracked region detection. These results show that the proposed computer-aided system can be used to automatically sort cracked eggs in the food industry.
Anahtar Kelimeler
Egg cracked detection Faster convolutional neural networks Computer aided detection system Segmentation Average precision
Proje Numarası
2180160
Kaynakça
- [1] N. Öztürk, “Görüntü işleme teknikleri ile beyaz yumurtalar üzerindeki yumurta kabuğu kusurlarının algılanması,” Yüksek Lisans Tez, Karadeniz Teknik Üniversitesi, Trabzon, Turkiye, 2014.
- [2] İ. Durmuş, E. Yenice and Ş. E. Demirtaş, “Egg abnormality,” Tavukçuluk Araştırma Dergisi, vol. 7, no. 1, pp. 66-71, 2007.
- [3] J. Priyadumkol, C. Kittichaikarn, and S. Thainimit, “Crack detection on unwashed eggs using image processing,” Journal of Food Engineering, vol. 209, pp. 76-82, 2007.
- [4] N. Öztürk and A. Gangal, “Eggshell defects detection on white eggs using image processing techniques,” In 2014 22nd Signal Processing and Communications Applications Conference (SIU), pp. 810-813, 2014.
- [5] M. Omid, M. Soltani, M. H. Dehrouyeh, S. S. Mohtasebi and H. Ahmadi, “An expert egg grading system based on machine vision and artificial intelligence techniques,” Journal of food engineering, vol. 118, no. 1, pp. 70-77, 2013.
- [6] B. Guanjun, J. Mimi, X. Yi, C. Shibo and Y. Qinghua, “Cracked egg recognition based on machine vision,” Computers and Electronics in Agriculture, vol. 158, pp. 159-166, 2019.
- [7] L. Wu, Q. Wang, D. Jie, S. Wang, Z. Zhu and L. Xiong, “Detection of crack eggs by image processing and soft-margin support vector machine,” Journal of Computational Methods in Sciences and Engineering, vol. 18, no. 1, pp. 21-31, 2018.
- [8] Y. Abbaspour-Gilandeh, and A. Azizi, “Identification of Cracks in Eggs Shell Using Computer Vision and Hough Transform,” Yüzüncü Yıl Üniversitesi Tarım Bilimleri Dergisi, vol. 28, no. 4, pp. 375-383, 2018.
- [9] J. Yang, C. Y. Xia, H. Pan, Y. Shi, and X. Y. Li, “Research of Test Model for Eggshell Crack Detection,” Advanced Materials Research. Vol. 846, Trans Tech Publications Ltd, 2014.
- [10] M. H. Abdullah, S. Nashat, S. A. Anwar and M. Z. Abdullah, “A framework for crack detection of fresh poultry eggs at visible radiation,” Computers and Electronics in Agriculture, vol. 141, pp. 81-95, 2017.
- [11] A. K. Datta, B. Botta and S. S. R. Gattam, “Damage detection on chicken eggshells using Faster R-CNN,” 2019 ASABE Annual International Meeting. American Society of Agricultural and Biological Engineers, 2019.
- [12] Q. Li, and G. Chen, “Recognition of industrial machine parts based on transfer learning with convolutional neural network,” Plos one, vol. 16, no. 1, pp. e0245735, 2021.
- [13] M. Turkoglu, “COVIDetectioNet: COVID-19 diagnosis system based on X-ray images using features selected from pre-learned deep features ensemble,” Applied Intelligence, pp. 1-14, 2020.
- [14] S. K. Khare, and V. Bajaj, “Time-frequency representation and convolutional neural network-based emotion recognition,” IEEE transactions on neural networks and learning systems, pp. 1-9, 2020.
- [15] F. Demir, M. Turkoglu, M. Aslan, and A. Sengur, “A new pyramidal concatenated CNN approach for environmental sound classification,” Applied Acoustics, vol. 170, pp. 107520, 2020.
- [16] D. Şengür and S. Siuly, “Efficient approach for EEG-based emotion recognition,” Electronics Letters, vol. 56, no. 25, pp. 1361-1364, 2020.
- [17] M. B. ER, “Akciğer Seslerinin Derin Öğrenme ile Sınıflandırılması,” Gazi Üniversitesi Fen Bilimleri Dergisi Part C: Tasarım ve Teknoloji, vol. 8, no. 4, pp. 830-844, 2020.
- [18] Y. Guo, Y. Peng and B. Zhang, “CAFR-CNN: coarse-to-fine adaptive faster R-CNN for cross-domain joint optic disc and cup segmentation,” Applied Intelligence, pp. 1-25, 2021.
- [19] S. Ren, K. He, R. Girshick and J. Sun, “Faster R-CNN: towards real-time object detection with region proposal networks,” IEEE transactions on pattern analysis and machine intelligence, vol. 39, no. 6, pp. 1137-1149, 2016.
Ayrıntılar
| Birincil Dil | Türkçe |
|---|---|
| Konular | Mühendislik |
| Bölüm | Tasarım ve Teknoloji |
| Yazarlar | |
| Proje Numarası | 2180160 |
| Yayımlanma Tarihi | 25 Mart 2021 |
| Gönderilme Tarihi | 10 Şubat 2021 |
| Yayımlandığı Sayı | Yıl 2021 Cilt: 9 Sayı: 1 |
