Daha Hızlı Bölgesel-Evrişimsel Sinir Ağları ile Sığır Yüzlerinin Tanınması
Year 2019,
Volume: 6, 177 - 189, 30.09.2019
Emre Dandıl
,
Musa Turkan
,
Mustafa Boğa
,
Kerim Kürşat Çevik
Abstract
Süt sığırcılığı işletmelerinde
sürülerinin yönetilmesinden ziyade ineklerin bireysel olarak refahı ve sağlıklı
olmasına yönelik hassasiyet son yıllarda artmıştır. Bu durumun sonucu
olarak, bireysel olarak hayvanların takip edilme ihtiyacı ortaya çıkmıştır.
Hayvanlar
için biyometrik veriler kullanılarak oluşturulacak sistemler, hayvanları
bireysel olarak tanınmasına yardımcı olmaktadır. Hayvanlardan
elde edilen yüz, burun, iris gibi bireysel biyometrik veriler işlenerek makine
öğrenmesi temelli sistemler oluşturulabilir. Bu
çalışmada, derin öğrenmede önemli bir model olan Daha Hızlı Bölgesel-Evrişimsel
Sinir Ağları(DHB-ESA) kullanılarak, sığırların yüz görüntülerinin
sınıflandırılarak tanınması gerçekleştirilmiştir. Çalışmada
öncelikle, bir besi yerinde bulunan sığırlardan yüz görüntülerini içeren
görüntüleri alınarak bir veriseti oluşturulmuştur. Daha
sonra, sığır görüntülerindeki yüz bölgeleri, uygulama ile işaretlenerek sığır
sınıflarına göre etiketlenmiştir. Deneysel çalışmalar
kapsamında, veriseti içerisinden beş farklı sığıra ait toplamda 1579 görüntüden
oluşan bir alt küme oluşturulmuştur. Bu küme, ağın
eğitimi için 1129 görüntü ve test işlemi için ise 450 görüntü olacak şekilde
gruplandırılmıştır. Sığır yüz görüntüleri ön-eğitimli
bir ağ üzerinde eğitildikten sonra, gerçekleştirilen test işlemlerinde sığır
yüz görüntüleri %98.44 doğruluk ile başarılı bir şekilde sınıflandırılmıştır.
Önerilen
bilgisayar destekli bu yaklaşımın, sığırların yüzlerinin tanınmasında ikincil
bir araç olarak uzmanlar tarafından farklı amaçlar için kullanılabileceği
öngörülmektedir.
References
- [1] Kumar, S., Singh, S. K., Singh, A. K., Tiwari, S., & Singh, R. S. (2018). Privacy preserving security using biometrics in cloud computing. Multimedia Tools and Applications, 77, pp. 11017-11039.
- [2] Gaber, T., Tharwat, A., Hassanien, A. E., & Snasel, V. (2016). Biometric cattle identification approach based on weber’s local descriptor and adaboost classifier. Computers and Electronics in Agriculture, 122, 55-66.
- [3] Marchant, J. (2002). Secure animal identification and source verification. JM Communications, UK, 1-28.
- [4] Allen, A., Golden, B., Taylor, M., Patterson, D., Henriksen, D., & Skuce, R (2008). Evaluation of retinal imaging technology for the biometric identification of bovine animals in Northern Ireland. Livestock science, 116, 42-52.
- [5] Shanahan, C., Kernan, B., Ayalew, G., McDonnell, K., Butler, F., & Ward, S. (2009). A framework for beef traceability from farm to slaughter using global standards: an Irish perspective. Computers and electronics in agriculture, 66, 62-69.
- [6] Noviyanto A., & Arymurthy, A. M. (2013). Beef cattle identification based on muzzle pattern using a matching refinement technique in the SIFT method. Computers and Electronics in Agriculture, 99, 77-84.
- [7] Rojas-Olivares, M., Caja, G., Carné, S., Salama, A., Adell, N., & Puig, P. (2011). Retinal image recognition for verifying the identity of fattening and replacement lambs. Journal of animal science, 89, 2603-2613.
- [8] Barry, B., Corkery, G., Gonzales-Barron, U., Mc Donnell, K., Butler, F., & S. Ward, (2008). A longitudinal study of the effect of time on the matching performance of a retinal recognition system for lambs. Computers and electronics in agriculture, 64, 202-211.
- [9] Kühl H. S., & T. Burghardt, (2013). Animal biometrics: quantifying and detecting phenotypic appearance. Trends in ecology & evolution, 28, 432-441.
- [10] Kumar S., & Singh, S. K. (2016). Visual animal biometrics: survey. IET Biometrics, 6, 139-156.
- [11] Boğa M., Burğut, A. (2018). Görüntü İşleme Yöntemi Kullanılarak Kümes Hayvanlarında Davranışlarının Tahmini, International Congress on Domastic Animal Breeding Genetics and Husbandary (ICABGEH-2018), Antalya.
- [12] Kashiha, M. A., Bahr, C., Vranken, E., Hong, S., & Berckmans, D. (2017). Monitoring system to detect problems in broiler houses based on image processing. Int. Conf. Agric. Eng, 2014, pp. 6-10.
- [13] Shalika A. U., & Seneviratne, L. (2016). Animal Classification System Based on Image Processing & Support Vector Machine. Journal of Computer and Communications, 4, 12.
- [14] Parikh, M., Patel, M., & Bhatt, D., Animal detection using template matching algorithm. International Journal of Research in Modern Engineering and Emerging Technology, 1, 26-32.
- [15] Awad, A. I. (2016). From classical methods to animal biometrics: A review on cattle identification and tracking. Computers and Electronics in Agriculture, 123, 423-435.
- [16] Awad, A. I., Zawbaa, H. M., Mahmoud, H. A., Nabi, E. H. H. A., Fayed, R. H., & A. E. Hassanien, (2013). A robust cattle identification scheme using muzzle print images. Federated Conference on Computer Science and Information Systems, 2013, 529-534.
- [17] Kumar, S., Tiwari, S., & Singh, S. K. (2015). Face recognition for cattle. Third International Conference on Image Information Processing (ICIIP), 2015, 65-72.
- [18] Barron, U. G., Corkery, G., Barry, B., Butler, F., McDonnell, K., & Ward, S., (2008). Assessment of retinal recognition technology as a biometric method for sheep identification. Computers and electronics in agriculture, 60, 156-166.
- [19] Minagawa, H., Fujimura, T., Ichiyanagi, M., Tanaka, K., & Fangquan, M., (2002). Identification of beef cattle by analyzing images of their muzzle patterns lifted on paper. Publications of the Japanese Society of Agricultural Informatics, 8, 596-600.
- [20] Tharwat, A., Gaber, T., Hassanien, A. E., Hassanien, H. A., & Tolba, M. F., (2014). Cattle identification using muzzle print images based on texture features approach. Fifth International Conference on Innovations in Bio-Inspired Computing and Applications IBICA 2014, 217-227.
- [21] Kumar, S., Pandey, A., Satwik, K. S. R., Kumar, S., Singh, S. K., Singh, A. K., et al., (2018). Deep learning framework for recognition of cattle using muzzle point image pattern. Measurement, 116, 1-17.
- [22] Mahmoud, H. A., & Hadad, H. M. R. E., (2015). Automatic cattle muzzle print classification system using multiclass support vector machine. International Journal of Image Mining, 1, 126-140.
- [23] Zin, T. T., Phyo, C. N., Tin, P., Hama, H., & Kobayashi, I., (2018). Image technology based cow identification system using deep learning. International MultiConference of Engineers and Computer Scientists.
- [24] Kim, H. T., Choi, H. L., Lee, D. W., & Yoon, Y. C., (2005). Recognition of individual Holstein cattle by imaging body patterns. Asian-australasian journal of animal sciences, 18, 1194-1198.
- [25] Sun, S., Yang, S., & Zhao, L., (2013). Noncooperative bovine iris recognition via SIFT. Neurocomputing, 120, 310-317.
- [26] Lu, Y., He, X., Wen, Y., & Wang, P. S. (2014). A new cow identification system based on iris analysis and recognition. International Journal of Biometrics, 6, 18-32.
- [27] Faster R-CNN Inception V2 Coco. Faster RCNN Inception V2 Coco, (2019) https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/detection_model_zoo.md, (13.07.2019).
- [28] Andrew, N, (2018). Unsupervised Feature Learning and Deep Learning Tutorial, http://deeplearning.stanford.edu/tutorial/supervised/ConvolutionalNeuralNetwork/, (07.07.2019)
- [29] Koppula H. S., & Saxena, A., (2015). Anticipating human activities using object affordances for reactive robotic response. IEEE transactions on pattern analysis and machine intelligence, 38, 14-29.
- [30] Lu, Y., Yi, S., Zeng, N., Liu, Y., & Zhang, Y., (2017). Identification of rice diseases using deep convolutional neural networks. Neurocomputing, 267, 378-384.
- [31] Ali A., & Hanbay, D., (2018). Bölgesel evrişimsel sinir ağları tabanlı MR görüntülerinde tümör tespiti. Gazi Üniversitesi Mühendislik-Mimarlık Fakültesi Dergisi, 2018.
- [32] Özkan İ., & Ülker, E., (2017). Derin Öğrenme ve Görüntü Analizinde Kullanılan Derin Öğrenme Modelleri. Gaziosmanpaşa Bilimsel Araştırma Dergisi, 6, 85-104.
- [33] Ren, S., He, K., Girshick, R., & Sun, J., (2015). Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems, 2015, 91-99.
- [34] Rohith. G., (2018). R-CNN, Fast R-CNN, Faster R-CNN, YOLO — Object Detection Algorithms. https://towardsdatascience.com/r-cnn-fast-r-cnn-faster-r-cnn-yolo-object-detection-algorithms-36d53571365e, (07.07.2019).
- [35] LabelImage. https://github.com/tzutalin/labelImg, (13.07.2019).
Recognition of Cattle Faces Using the Faster R-CNN
Year 2019,
Volume: 6, 177 - 189, 30.09.2019
Emre Dandıl
,
Musa Turkan
,
Mustafa Boğa
,
Kerim Kürşat Çevik
Abstract
Sensitivity to individual
welfare and health of cows has increased in recent years rather than managing
herds in dairy cattle holdings. As a result of this situation, the need to
follow the animals individually emerged. Systems for animals using biometric data
help identify animals individually. Machine learning based systems can be
created by processing individual biometric data such as face, muzzle, iris from
animals. In this study, facial images of cattle are classified and identified
using faster regional-convolutional neural networks (faster R-CNN), which is an
important model in deep learning. In the study, firstly, a dataset containing
face images is obtained from cattle in a fattening site. The facial regions in
the cattle images are then labelled by application according to cattle classes.
Within the scope of experimental studies, a subset of 1579 images of five different
cattle is created from the dataset. This subset is grouped into 1129 images for
network training and 450 images for testing. After training on a pre-trained
network of cattle face images, cattle face images are successfully classified
with 98.44% accuracy in the performed test procedures. It is envisaged that
this proposed computer-aided approach can be used by experts as a secondary
tool in recognizing the faces of cattle for different purposes.
References
- [1] Kumar, S., Singh, S. K., Singh, A. K., Tiwari, S., & Singh, R. S. (2018). Privacy preserving security using biometrics in cloud computing. Multimedia Tools and Applications, 77, pp. 11017-11039.
- [2] Gaber, T., Tharwat, A., Hassanien, A. E., & Snasel, V. (2016). Biometric cattle identification approach based on weber’s local descriptor and adaboost classifier. Computers and Electronics in Agriculture, 122, 55-66.
- [3] Marchant, J. (2002). Secure animal identification and source verification. JM Communications, UK, 1-28.
- [4] Allen, A., Golden, B., Taylor, M., Patterson, D., Henriksen, D., & Skuce, R (2008). Evaluation of retinal imaging technology for the biometric identification of bovine animals in Northern Ireland. Livestock science, 116, 42-52.
- [5] Shanahan, C., Kernan, B., Ayalew, G., McDonnell, K., Butler, F., & Ward, S. (2009). A framework for beef traceability from farm to slaughter using global standards: an Irish perspective. Computers and electronics in agriculture, 66, 62-69.
- [6] Noviyanto A., & Arymurthy, A. M. (2013). Beef cattle identification based on muzzle pattern using a matching refinement technique in the SIFT method. Computers and Electronics in Agriculture, 99, 77-84.
- [7] Rojas-Olivares, M., Caja, G., Carné, S., Salama, A., Adell, N., & Puig, P. (2011). Retinal image recognition for verifying the identity of fattening and replacement lambs. Journal of animal science, 89, 2603-2613.
- [8] Barry, B., Corkery, G., Gonzales-Barron, U., Mc Donnell, K., Butler, F., & S. Ward, (2008). A longitudinal study of the effect of time on the matching performance of a retinal recognition system for lambs. Computers and electronics in agriculture, 64, 202-211.
- [9] Kühl H. S., & T. Burghardt, (2013). Animal biometrics: quantifying and detecting phenotypic appearance. Trends in ecology & evolution, 28, 432-441.
- [10] Kumar S., & Singh, S. K. (2016). Visual animal biometrics: survey. IET Biometrics, 6, 139-156.
- [11] Boğa M., Burğut, A. (2018). Görüntü İşleme Yöntemi Kullanılarak Kümes Hayvanlarında Davranışlarının Tahmini, International Congress on Domastic Animal Breeding Genetics and Husbandary (ICABGEH-2018), Antalya.
- [12] Kashiha, M. A., Bahr, C., Vranken, E., Hong, S., & Berckmans, D. (2017). Monitoring system to detect problems in broiler houses based on image processing. Int. Conf. Agric. Eng, 2014, pp. 6-10.
- [13] Shalika A. U., & Seneviratne, L. (2016). Animal Classification System Based on Image Processing & Support Vector Machine. Journal of Computer and Communications, 4, 12.
- [14] Parikh, M., Patel, M., & Bhatt, D., Animal detection using template matching algorithm. International Journal of Research in Modern Engineering and Emerging Technology, 1, 26-32.
- [15] Awad, A. I. (2016). From classical methods to animal biometrics: A review on cattle identification and tracking. Computers and Electronics in Agriculture, 123, 423-435.
- [16] Awad, A. I., Zawbaa, H. M., Mahmoud, H. A., Nabi, E. H. H. A., Fayed, R. H., & A. E. Hassanien, (2013). A robust cattle identification scheme using muzzle print images. Federated Conference on Computer Science and Information Systems, 2013, 529-534.
- [17] Kumar, S., Tiwari, S., & Singh, S. K. (2015). Face recognition for cattle. Third International Conference on Image Information Processing (ICIIP), 2015, 65-72.
- [18] Barron, U. G., Corkery, G., Barry, B., Butler, F., McDonnell, K., & Ward, S., (2008). Assessment of retinal recognition technology as a biometric method for sheep identification. Computers and electronics in agriculture, 60, 156-166.
- [19] Minagawa, H., Fujimura, T., Ichiyanagi, M., Tanaka, K., & Fangquan, M., (2002). Identification of beef cattle by analyzing images of their muzzle patterns lifted on paper. Publications of the Japanese Society of Agricultural Informatics, 8, 596-600.
- [20] Tharwat, A., Gaber, T., Hassanien, A. E., Hassanien, H. A., & Tolba, M. F., (2014). Cattle identification using muzzle print images based on texture features approach. Fifth International Conference on Innovations in Bio-Inspired Computing and Applications IBICA 2014, 217-227.
- [21] Kumar, S., Pandey, A., Satwik, K. S. R., Kumar, S., Singh, S. K., Singh, A. K., et al., (2018). Deep learning framework for recognition of cattle using muzzle point image pattern. Measurement, 116, 1-17.
- [22] Mahmoud, H. A., & Hadad, H. M. R. E., (2015). Automatic cattle muzzle print classification system using multiclass support vector machine. International Journal of Image Mining, 1, 126-140.
- [23] Zin, T. T., Phyo, C. N., Tin, P., Hama, H., & Kobayashi, I., (2018). Image technology based cow identification system using deep learning. International MultiConference of Engineers and Computer Scientists.
- [24] Kim, H. T., Choi, H. L., Lee, D. W., & Yoon, Y. C., (2005). Recognition of individual Holstein cattle by imaging body patterns. Asian-australasian journal of animal sciences, 18, 1194-1198.
- [25] Sun, S., Yang, S., & Zhao, L., (2013). Noncooperative bovine iris recognition via SIFT. Neurocomputing, 120, 310-317.
- [26] Lu, Y., He, X., Wen, Y., & Wang, P. S. (2014). A new cow identification system based on iris analysis and recognition. International Journal of Biometrics, 6, 18-32.
- [27] Faster R-CNN Inception V2 Coco. Faster RCNN Inception V2 Coco, (2019) https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/detection_model_zoo.md, (13.07.2019).
- [28] Andrew, N, (2018). Unsupervised Feature Learning and Deep Learning Tutorial, http://deeplearning.stanford.edu/tutorial/supervised/ConvolutionalNeuralNetwork/, (07.07.2019)
- [29] Koppula H. S., & Saxena, A., (2015). Anticipating human activities using object affordances for reactive robotic response. IEEE transactions on pattern analysis and machine intelligence, 38, 14-29.
- [30] Lu, Y., Yi, S., Zeng, N., Liu, Y., & Zhang, Y., (2017). Identification of rice diseases using deep convolutional neural networks. Neurocomputing, 267, 378-384.
- [31] Ali A., & Hanbay, D., (2018). Bölgesel evrişimsel sinir ağları tabanlı MR görüntülerinde tümör tespiti. Gazi Üniversitesi Mühendislik-Mimarlık Fakültesi Dergisi, 2018.
- [32] Özkan İ., & Ülker, E., (2017). Derin Öğrenme ve Görüntü Analizinde Kullanılan Derin Öğrenme Modelleri. Gaziosmanpaşa Bilimsel Araştırma Dergisi, 6, 85-104.
- [33] Ren, S., He, K., Girshick, R., & Sun, J., (2015). Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems, 2015, 91-99.
- [34] Rohith. G., (2018). R-CNN, Fast R-CNN, Faster R-CNN, YOLO — Object Detection Algorithms. https://towardsdatascience.com/r-cnn-fast-r-cnn-faster-r-cnn-yolo-object-detection-algorithms-36d53571365e, (07.07.2019).
- [35] LabelImage. https://github.com/tzutalin/labelImg, (13.07.2019).