Gömülü Derin Öğrenme ile Tehdit İçeren Nesnelerin Gerçek Zamanda Tespiti
Yıl 2019,
Cilt: 10 Sayı: 2, 497 - 509, 20.06.2019
Mehmet Umut Salur
,
İlhan Aydın
,
Mehmet Karaköse
Öz
Derin
öğrenme metotları bilgisayarlı görme ve görüntü işlemede özellikle de görüntü
sınıflandırma probleminde önemli bir teknoloji haline gelmiştir. Bunun en
önemli nedenlerinden biri farklı problemler üzerinde derin öğrenmenin göstermiş
olduğu üstün başarıdır. İnternetin gelişimi ile çok büyük veri kümeleri
toplanmakta ve yüksek güçlü grafik işlemci kartlar ile bu veriler gerçek
zamanlı olarak işlenebilmektedir. Fakat her problemler için bu şekilde büyük
ölçekli veri toplamak oldukça maliyetli bir işlemdir. Bu amaçla ön eğitilmiş
derin öğrenme modelleri transfer öğrenme yöntemi ile daha düşük boyuttaki
verileri sınıflandırmak için kullanılabilir. Bu çalışmada X-ray cihazlarından
alınan görüntülerde tehdit unsuru içeren nesneleri sınıflandırmak için transfer
öğrenme yöntemi ile gömülü ve gerçek zamanlı çalışabilen bir sistem
geliştirilmiştir. Bu sistem Nvidia Jetson TX2 geliştirme kartı üzerinde bir
evrişimsel sinir ağı olan Alexnet derin öğrenme modeli kullanmaktadır. Bu model
ile X-ray bagaj güvenlik görüntüleri içerisindeki bıçak, silah, jilet ve Ninja
yıldızı gibi tehdit unsuru içeren nesneler sınıflandırılmıştır. Oluşturulan deney ortamında Alexnet 12.000
görüntü ile eğitilmiş ve gerçek ortamda test edilmiştir. Önerilen yöntemin
performansı aynı veri kümesi üzerinde daha önce yapılan farklı bilgisayarlı
görme teknikleri ile karşılaştırılmış ve daha başarılı sonuçlar elde edilmiştir.
Kaynakça
- Baştan, M., Yousefi, M. R., & Breuel, T. M. (2011). Visual words on baggage X-ray images. Computer analysis of images and patterns, 360-368, Springer, Berlin, Heidelberg.
- Chen, Y. (2015). Convolutional Neural Network for Sentence Classification, Yüksek lisans tezi, University of Waterloo, Kanada.
- Gu, J., Wang, Z., Kuen, J., Ma, L., Shahroudy, A., Shuai, B., ... & Chen, T. (2018). Recent advances in convolutional neural networks, Pattern Recognition, 77, 354-377.
- He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition, Proceedings, IEEE Conference on Computer Vision and Pattern Recognition, 770-778.
- Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory, Neural Computation, 9, 8, 1735-1780.
- Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., ... & Darrell, T. (2014, November). Caffe: Convolutional architecture for fast feature embedding, Proceedings, 22nd ACM international conference on Multimedia, 675-678.
- Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks, Advances in neural information processing systems, 25, 1097-1105.
- LeCun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998). Gradient-based learning applied to document recognition, Proceedings of the IEEE, 86, 11, 2278-2324.
- LeCun, Y. 2015. LeNet-5, Convolutional Neural Networks. URL: http://yann.lecun.com/exdb/lenet/. Erişim tarihi: 12 Ekim 2018.
- Mery, D., Svec, E., Arias, M., Riffo, V., Saavedra, J. M., & Banerjee, S. (2017). Modern computer vision techniques for x-ray testing in baggage inspection, IEEE Transactions on Systems, Man, and Cybernetics: Systems, 47, 4, 682-692.
- Mery, D., Svec, E., & Arias, M. (2016). Object recognition in X-ray testing using adaptive sparse representations, Journal of Nondestructive Evaluation, 35, 3, 45.
- Mery, D., Svec, E., & Arias, M. (2015, November). Object recognition in baggage inspection using adaptive sparse representations of X-ray images, Proceedings, Pacific-Rim Symposium on Image and Video Technology, 709-720, Springer, Cham.
- Niu, X. X., & Suen, C. Y. (2012). A novel hybrid CNN–SVM classifier for recognizing handwritten digits, Pattern Recognition, 45, 4, 1318-1325.
- Parliament, E. (2012). Aviation security with a special focus on security scanners. European Parliament Resolution (2010/2154 (INI)), 1-10.
- Ponti, M. A., Ribeiro, L. S. F., Nazare, T. S., Bui, T., & Collomosse, J. (2017, October). Everything you wanted to know about Deep Learning for Computer Vision but were afraid to ask. In Graphics, Patterns and Images Tutorials (SIBGRAPI-T), 2017 30th SIBGRAPI Conference, 17-41.
- Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., ... & Berg, A. C. (2015). Imagenet large scale visual recognition challenge, International Journal of Computer Vision, 115, 3, 211-252.
- Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition, arXiv preprint arXiv:1409.1556.Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., ... & Rabinovich, A. (2015). Going deeper with convolutions, Proceedings IEEE Conference on Computer Vision and Pattern Recognition, 1-9.
- Riffo, V., & Mery, D. (2016). Automated detection of threat objects using adapted implicit shape model, IEEE Transactions on Systems, Man, and Cybernetics: Systems, 46, 4, 472-482.
- Ren, S., He, K., Girshick, R., & Sun, J. (2017). Faster R-CNN: towards real-time object detection with region proposal networks, IEEE Transactions on Pattern Analysis & Machine Intelligence, 6, 1137-1149.
- Salur, M. U., & Aydin, İ. (2018, May). Sentiment classification based on deep learning, Proceedings, IEEE 26th Signal Processing and Communications Applications Conference (SIU), 1-4, İzmir.
- Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., ... & Rabinovich, A. (2015). Going deeper with convolutions, Proceedings IEEE Conference on Computer Vision and Pattern Recognition, 1-9.
Yıl 2019,
Cilt: 10 Sayı: 2, 497 - 509, 20.06.2019
Mehmet Umut Salur
,
İlhan Aydın
,
Mehmet Karaköse
Kaynakça
- Baştan, M., Yousefi, M. R., & Breuel, T. M. (2011). Visual words on baggage X-ray images. Computer analysis of images and patterns, 360-368, Springer, Berlin, Heidelberg.
- Chen, Y. (2015). Convolutional Neural Network for Sentence Classification, Yüksek lisans tezi, University of Waterloo, Kanada.
- Gu, J., Wang, Z., Kuen, J., Ma, L., Shahroudy, A., Shuai, B., ... & Chen, T. (2018). Recent advances in convolutional neural networks, Pattern Recognition, 77, 354-377.
- He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition, Proceedings, IEEE Conference on Computer Vision and Pattern Recognition, 770-778.
- Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory, Neural Computation, 9, 8, 1735-1780.
- Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., ... & Darrell, T. (2014, November). Caffe: Convolutional architecture for fast feature embedding, Proceedings, 22nd ACM international conference on Multimedia, 675-678.
- Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks, Advances in neural information processing systems, 25, 1097-1105.
- LeCun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998). Gradient-based learning applied to document recognition, Proceedings of the IEEE, 86, 11, 2278-2324.
- LeCun, Y. 2015. LeNet-5, Convolutional Neural Networks. URL: http://yann.lecun.com/exdb/lenet/. Erişim tarihi: 12 Ekim 2018.
- Mery, D., Svec, E., Arias, M., Riffo, V., Saavedra, J. M., & Banerjee, S. (2017). Modern computer vision techniques for x-ray testing in baggage inspection, IEEE Transactions on Systems, Man, and Cybernetics: Systems, 47, 4, 682-692.
- Mery, D., Svec, E., & Arias, M. (2016). Object recognition in X-ray testing using adaptive sparse representations, Journal of Nondestructive Evaluation, 35, 3, 45.
- Mery, D., Svec, E., & Arias, M. (2015, November). Object recognition in baggage inspection using adaptive sparse representations of X-ray images, Proceedings, Pacific-Rim Symposium on Image and Video Technology, 709-720, Springer, Cham.
- Niu, X. X., & Suen, C. Y. (2012). A novel hybrid CNN–SVM classifier for recognizing handwritten digits, Pattern Recognition, 45, 4, 1318-1325.
- Parliament, E. (2012). Aviation security with a special focus on security scanners. European Parliament Resolution (2010/2154 (INI)), 1-10.
- Ponti, M. A., Ribeiro, L. S. F., Nazare, T. S., Bui, T., & Collomosse, J. (2017, October). Everything you wanted to know about Deep Learning for Computer Vision but were afraid to ask. In Graphics, Patterns and Images Tutorials (SIBGRAPI-T), 2017 30th SIBGRAPI Conference, 17-41.
- Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., ... & Berg, A. C. (2015). Imagenet large scale visual recognition challenge, International Journal of Computer Vision, 115, 3, 211-252.
- Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition, arXiv preprint arXiv:1409.1556.Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., ... & Rabinovich, A. (2015). Going deeper with convolutions, Proceedings IEEE Conference on Computer Vision and Pattern Recognition, 1-9.
- Riffo, V., & Mery, D. (2016). Automated detection of threat objects using adapted implicit shape model, IEEE Transactions on Systems, Man, and Cybernetics: Systems, 46, 4, 472-482.
- Ren, S., He, K., Girshick, R., & Sun, J. (2017). Faster R-CNN: towards real-time object detection with region proposal networks, IEEE Transactions on Pattern Analysis & Machine Intelligence, 6, 1137-1149.
- Salur, M. U., & Aydin, İ. (2018, May). Sentiment classification based on deep learning, Proceedings, IEEE 26th Signal Processing and Communications Applications Conference (SIU), 1-4, İzmir.
- Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., ... & Rabinovich, A. (2015). Going deeper with convolutions, Proceedings IEEE Conference on Computer Vision and Pattern Recognition, 1-9.