Yıl: 2020 Cilt: 3 Sayı: 3 Sayfa Aralığı: 264 - 271 Metin Dili: İngilizce DOI: 10.35377/saucis.03.03.725647 İndeks Tarihi: 15-05-2021

An Evaluation of VGG16 Binary Classifier Deep Neural Network for Noise and Blur Corrupted Images

Öz:
Deep learning networks has become an important tool for image classification applications. Distortions on imagesmay cause the performance of a classifier to decrease significantly. In the present paper, a comparativeinvestigation for binary classification performance of VGG16 network under corrupted inputs has been presented.For this purpose, images corrupted at various levels and fixed levels with Gaussian noise, Salt and Pepper noiseand blur effect were used for testing. Convolutional layers of the VGG16 were frozen except the last threeconvolutional layers and a dense layer for binary classification was added. According to experimental results, asthe effect of distortion is increased, performance of the deep learning classifier drops significantly. In the case ofaugmented training with distortion effects, the results were improved significantly
Anahtar Kelime:

VGG16 İkili Sınıflandırıcı Derin Sinir Ağının Gürültülü ve Bulanık Görüntüler için Değerlendirilmesi

Öz:
Derin öğrenme ağları, görüntü sınıflandırma uygulamaları için önemli bir araç haline gelmiştir. Görüntülerdeki bozulmalar, sınıflandırıcının performansının önemli ölçüde düşmesine neden olabilir. Bu makalede, bozuk girişler altında VGG16 ağının ikili sınıflandırma performansı için karşılaştırmalı bir araştırma sunulmuştur. Bu amaçla, çeşitli seviyelerde bozulmuş görüntüler ve Gauss gürültüsü, Tuz ve Biber gürültüsü ve bulanıklık etkisi ile sabit seviyelerde görüntüler test için kullanılmıştır. VGG16'nın evrişimli katmanları, son üç evrişimli katman hariç dondurulmuştur ve ikili sınıflandırma için yoğun bir katman eklenmiştir. Deneysel sonuçlara göre, bozulmanın etkisi arttıkça, derin öğrenme sınıflandırıcısının performansı önemli ölçüde düşmektedir. Bozulma etkilerini içeren artırılmış eğitim durumunda, sonuçlar önemli ölçüde iyileştirilmiştir.
Anahtar Kelime:

Belge Türü: Makale Makale Türü: Araştırma Makalesi Erişim Türü: Erişime Açık
  • [1] A. Voulodimos, N. Doulamis, A. Doulamis, and E. Protopapadakis, “Deep Learning for Computer Vision: A Brief Review,” Computational Intelligence and Neuroscience, vol. 2018. Hindawi Limited, 2018.
  • [2] T. Young, D. Hazarika, S. Poria, and E. Cambria, “Recent trends in deep learning based natural language processing,” ieee Comput. Intell. Mag., vol. 13, no. 3, pp. 55–75, 2018.
  • [3] H. Purwins, B. Li, T. Virtanen, J. Schlüter, S.-Y. Chang, and T. Sainath, “Deep learning for audio signal processing,” IEEE J. Sel. Top. Signal Process., vol. 13, no. 2, pp. 206–219, 2019.
  • [4] F. Altaf, S. M. S. Islam, N. Akhtar, and N. K. Janjua, “Going Deep in Medical Image Analysis: Concepts, Methods, Challenges, and Future Directions,” IEEE Access, vol. 7, pp. 99540– 99572, 2019.
  • [5] F. Chollet, “Keras,” GitHub repository. GitHub, 2015.
  • [6] M. Abadi et al., “TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems,” arXiv Prepr. arXiv1603.04467, 2016.
  • [7] D. Yu et al., “An introduction to computational networks and the computational network toolkit,” 2014.
  • [8] R. Al-Rfou et al., “Theano: A {Python} framework for fast computation of mathematical expressions,” arXiv e-prints, vol. abs/1605.0, May 2016.
  • [9] Y. LeCun et al., “Handwritten digit recognition with a back-propagation network,” in Advances in neural information processing systems, 1990, pp. 396–404.
  • [10] C. Shorten and T. M. Khoshgoftaar, “A survey on Image Data Augmentation for Deep Learning,” J. Big Data, vol. 6, no. 1, p. 60, 2019.
  • [11] S. Dodge and L. Karam, “Understanding how image quality affects deep neural networks,” in 2016 eighth international conference on quality of multimedia experience (QoMEX), 2016, pp. 1–6.
  • [12] S. Dodge and L. Karam, “A study and comparison of human and deep learning recognition performance under visual distortions,” in 2017 26th international conference on computer communication and networks (ICCCN), 2017, pp. 1–7.
  • [13] I. Vasiljevic, A. Chakrabarti, and G. Shakhnarovich, “Examining the impact of blur on recognition by convolutional networks,” arXiv Prepr. arXiv1611.05760, 2016.
  • [14] D. Yin, R. G. Lopes, J. Shlens, E. D. Cubuk, and J. Gilmer, “A fourier perspective on model robustness in computer vision,” in Advances in Neural Information Processing Systems, 2019, pp. 13255–13265.
  • [15] E. Rusak et al., “Increasing the robustness of DNNs against image corruptions by playing the Game of Noise,” arXiv Prepr. arXiv2001.06057, 2020.
  • [16] C. Kamann and C. Rother, “Benchmarking the robustness of semantic segmentation models with respect to common corruptions,” Int. J. Comput. Vis., pp. 1–22, 2020.
  • [17] K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” arXiv Prepr. arXiv1409.1556, 2014.
APA Akgün D (2020). An Evaluation of VGG16 Binary Classifier Deep Neural Network for Noise and Blur Corrupted Images. , 264 - 271. 10.35377/saucis.03.03.725647
Chicago Akgün Devrim An Evaluation of VGG16 Binary Classifier Deep Neural Network for Noise and Blur Corrupted Images. (2020): 264 - 271. 10.35377/saucis.03.03.725647
MLA Akgün Devrim An Evaluation of VGG16 Binary Classifier Deep Neural Network for Noise and Blur Corrupted Images. , 2020, ss.264 - 271. 10.35377/saucis.03.03.725647
AMA Akgün D An Evaluation of VGG16 Binary Classifier Deep Neural Network for Noise and Blur Corrupted Images. . 2020; 264 - 271. 10.35377/saucis.03.03.725647
Vancouver Akgün D An Evaluation of VGG16 Binary Classifier Deep Neural Network for Noise and Blur Corrupted Images. . 2020; 264 - 271. 10.35377/saucis.03.03.725647
IEEE Akgün D "An Evaluation of VGG16 Binary Classifier Deep Neural Network for Noise and Blur Corrupted Images." , ss.264 - 271, 2020. 10.35377/saucis.03.03.725647
ISNAD Akgün, Devrim. "An Evaluation of VGG16 Binary Classifier Deep Neural Network for Noise and Blur Corrupted Images". (2020), 264-271. https://doi.org/10.35377/saucis.03.03.725647
APA Akgün D (2020). An Evaluation of VGG16 Binary Classifier Deep Neural Network for Noise and Blur Corrupted Images. Sakarya University Journal of Computer and Information Sciences (Online), 3(3), 264 - 271. 10.35377/saucis.03.03.725647
Chicago Akgün Devrim An Evaluation of VGG16 Binary Classifier Deep Neural Network for Noise and Blur Corrupted Images. Sakarya University Journal of Computer and Information Sciences (Online) 3, no.3 (2020): 264 - 271. 10.35377/saucis.03.03.725647
MLA Akgün Devrim An Evaluation of VGG16 Binary Classifier Deep Neural Network for Noise and Blur Corrupted Images. Sakarya University Journal of Computer and Information Sciences (Online), vol.3, no.3, 2020, ss.264 - 271. 10.35377/saucis.03.03.725647
AMA Akgün D An Evaluation of VGG16 Binary Classifier Deep Neural Network for Noise and Blur Corrupted Images. Sakarya University Journal of Computer and Information Sciences (Online). 2020; 3(3): 264 - 271. 10.35377/saucis.03.03.725647
Vancouver Akgün D An Evaluation of VGG16 Binary Classifier Deep Neural Network for Noise and Blur Corrupted Images. Sakarya University Journal of Computer and Information Sciences (Online). 2020; 3(3): 264 - 271. 10.35377/saucis.03.03.725647
IEEE Akgün D "An Evaluation of VGG16 Binary Classifier Deep Neural Network for Noise and Blur Corrupted Images." Sakarya University Journal of Computer and Information Sciences (Online), 3, ss.264 - 271, 2020. 10.35377/saucis.03.03.725647
ISNAD Akgün, Devrim. "An Evaluation of VGG16 Binary Classifier Deep Neural Network for Noise and Blur Corrupted Images". Sakarya University Journal of Computer and Information Sciences (Online) 3/3 (2020), 264-271. https://doi.org/10.35377/saucis.03.03.725647