Yüz Tanıma Sistemleri İçin Geliştirilmiş Veri Artırma Temelli Adaptif Yüz Tanıma Modeli

Abstract

Hızla gelişen bilgisayar ve grafik ara yüzüne sahip cihaz teknolojileri, yüz tanıma çalışmalarında yeni ufuklar açmışlardır. Özellikle derin öğrenme ağ mimari yapılarından biri olan evrişimsel sinir ağları (Convolutional Neural Network-CNN), yüz tanıma çalışmalarında büyük başarılar sağlamaktadır. Bu başarılar da veri setlerinin büyüklüğü önemli rol oynamaktadır. Özellikle kullanılan veri setlerindeki yetersizlik başarı oranlarını etkileyebilmektedir. Bunun önüne geçmek için ise veri tipine göre değişik veri artırma teknikleri uygulanmaktadır. Yapılan bu çalışmada yüz tanımlama problemi için derin öğrenmeye dayalı adaptif bir yüz tanıma modeli (AYTM) geliştirildi. Geliştirilen bu model kontrast sınırlı uyarlanabilir histogram eşitleme (Contrast Limited Adaptive Histogram Equalization-CLAHE), CNN ve çok katmanlı algılayıcı (Multi Layer Perceptron-MLP)’ndan oluşmaktadır. İki farklı veri seti grubu kullanılarak geliştirilen modelin performans değerlendirilmesi yapılmıştır. Özellikle veri artırma işleminin model başarısını ciddi oranda artırdığı gözlendi ve veri artırma işleminin derin öğrenme uygulamalarında gerekliliği vurgulanmıştır.

Keywords

• Evrişimsel sinir ağları
• Veri arttırma
• Histogram eşitleme

Data Augmentation Based Adaptive Face Recognition Model Developed for Face Recognition Systems

Abstract

The rapidly developing computer and device technologies with graphical interfaces opened new horizons in face recognition studies. Especially Convolutional Neural Networks (CNN), which is one of the deep learning network architecture structures, provides great success in face recognition studies. The size of the datasets plays an important role in these achievements. Especially the inadequacy of the data sets used can affect the success rates. In order to prevent this, different data augmentation techniques are applied according to the data type. In this study, an adaptive face recognition model based on deep learning was developed for the face identification problem. This developed model consists of contrast limited adaptive histogram equalization (CLAHE), CNN and multi-layer perceptron (MLP). Performance evaluation of the model developed was made by using two different data set groups. In particular, it was observed that data augmentation significantly increased the success of the model, and the necessity of data augmentation in deep learning applications was emphasized.

Keywords

• Convolutional neural network
• Data augmentation
• Histogram equalization

References

1. [1] Y. Q. Li, , D. T. Lin, and Z. W. Yeh, “Improving Deep Learning for Face Verification Using Color Histogram Equalization Data Augmentation,” in Proceedings of the 5th World Congress on Electrical Engineering and Computer Systems and Sciences. 2019, Paper No. MVML 103, Prague, Czech Republic.
2. [2] Y. Zhou, D. Liu, and T. Huang, “Survey of face detection on low-quality images,” 13th IEEE international conference on automatic face & gesture recognition (FG 2018), 2018, pp. 769-773.
3. [3] V. Kazemi, and J. Sullivan, “One millisecond face alignment with an ensemble of regression trees,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2014, pp. 1867-1874.
4. [4] J. Zhang, X. Wu, J. Zhu, and S. C. H. Hoi, “Feature agglomeration networks for single stage face detection,” Neurocomputing, vol. 380, pp. 180-189, 2020.
5. [5] C. Ren, N. An, J. Wang, L. Li, B. Hu, and D. Shang, “Optimal parameters selection for BP neural network based on particle swarm optimization: A case study of wind speed forecasting,” Knowledge-based systems, vol. 56, pp. 226-239, 2014.
6. [6] P. Viola, and M.J. Jones, “Robust real-time face detection,” International journal of computer vision, vol. 57, no. 2, pp. 137-154, 2004.
7. [7] K. Cui, H. Cai, Y. Zhang, and H. Chen, “A face alignment method based on SURF features,” 10th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI), 2017, pp. 1-6.
8. [8] B. Ammour, T. Bouden, L. Boubchir, and S. Biad, “Face identification using local and global features,” 40th International Conference on Telecommunications and Signal Processing (TSP), 2017, pp. 784-788.

9. [9] L. Cuimei, Q. Zhiliang, J. Nan, and W. Jianhua, “Human face detection algorithm via Haar cascade classifier combined with three additional classifiers,” 13th IEEE International Conference on Electronic Measurement & Instruments (ICEMI), 2017, pp. 483-487.
10. [10] H. Shu, D. Chen, Y. Li, and S. Wang, “A highly accurate facial region network for unconstrained face detection,” IEEE international conference on image processing (ICIP), 2017, pp. 665-669.
11. [11] J. J. Lv, X. H. Shao, J. S. Huang, X. D. Zhou, and X. Zhou, “Data augmentation for face recognition,” Neurocomputing, vol. 230, pp. 184-196, 2017.
12. [12] M.R. Faraji, and X. Qi, “Face recognition under varying illuminations using logarithmic fractal dimension-based complete eight local directional patterns,” Neurocomputing, vol. 199, pp. 16-30, 2016.
13. [13] F. Shahali, A. Nazemi, and Z. Azimifar, “Single sample face identification utilizing sparse discriminative multi manifold embedding,” Artificial Intelligence and Signal Processing Conference (AISP), 2017, pp. 1-5.
14. [14] G. Bazoukis, S. Stavrakis, J. Zhou, S. C. Bollepalli, G. Tse, Q. Zhang, J. P. Singh and A. A. Armoundas, “Machine learning versus conventional clinical methods in guiding management of heart failure patients—a systematic review,” Heart failure reviews, vol. 26, no. 1, pp. 23-34, 2021.
15. [15] M. F. Aslan, K. Sabanci, and A. Durdu, “A CNN-based novel solution for determining the survival status of heart failure patients with clinical record data: numeric to image,” Biomedical Signal Processing and Control, vol. 68, p. 102716, 2021.
16. [16] J. W. Oh, and J. Jeong, “Data augmentation for bearing fault detection with a light weight CNN,” Procedia Computer Science, vol. 175, pp. 72-79, 2020.
17. [17] U.R. Acharya, H. Fujita, S. L. Oh, Y. Hagiwara, J. H. Tan, M. Adam, and R. S. Tan, “Deep convolutional neural network for the automated diagnosis of congestive heart failure using ECG signals,” Applied Intelligence, vol. 49, no. 1, pp. 16-27, 2019.
18. [18] M. A. Kızrak, ve B. Bolat, “Derin öğrenme ile kalabalık analizi üzerine detaylı bir araştırma,” Bilişim Teknolojileri Dergisi, c. 11, s. 3, ss. 263-286, 2018.
19. [19] S. Akkol, A. Akilli, and I. Cemal, “Comparison of artificial neural network and multiple linear regression for prediction of live weight in hair goats,” Yyu J. Agric. Sci, vol. 27, pp. 21-29, 2017.
20. [20] Hinton, G., L. Deng, D. Yu, G. E. Dahl, A. Mohamed, N. Jaitly, A. Senior, V. Vanhoucke, P. Nguyen, T. N. Sainath, and B. Kingsbury, “Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups,” IEEE Signal processing magazine, vol. 29, no. 6, pp. 82-97, 2012.
21. [21] G. Li, L. Liu, X. Wang, X. Dong, P. Zhao, and X. Feng, “Auto-tuning neural network quantization framework for collaborative inference between the cloud and edge,” International Conference on Artificial Neural Networks, 2018, pp. 402-411.
22. [22] E. D. Cubuk, B. Zoph, D. Mane, V. Vasudevan, and Q. V. Le, “Autoaugment: Learning augmentation strategies from data,” the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 113-123.
23. [23] V. Sharma, and R.N. Mir, “A comprehensive and systematic look up into deep learning based object detection techniques: A review,” Computer Science Review, vol. 38, p. 100301, 2020.
24. [24] C. Shorten, and T. M. Khoshgoftaar, “A survey on image data augmentation for deep learning,” Journal of Big Data, vol. 6, no. 1, pp. 1-48, 2019.
25. [25] E. Cagli, C. Dumas, and E. Prouff, “Convolutional neural networks with data augmentation against jitter-based countermeasures,” International Conference on Cryptographic Hardware and Embedded Systems, 2017, pp. 45-68.
26. [26] L. Perez, and J. Wang, “The effectiveness of data augmentation in image classification using deep learning,” arXiv preprint, arXiv:1712.04621, 2017.
27. [27] B. McFee, E. J. Humphrey, and J. P. Bello, “A software framework for musical data augmentation,” Proceedings of the 16th ISMIR Conference, 2015, pp. 248-254.
28. [28] J. Salamon, and J. P. Bello, “Deep convolutional neural networks and data augmentation for environmental sound classification,” IEEE Signal processing letters, vol. 24, no. 3, pp. 279-283. 2017.
29. [29] A. M. Reza, “Realization of the contrast limited adaptive histogram equalization (CLAHE) for real-time image enhancement,” Journal of VLSI signal processing systems for signal, image and video technology, vol. 38, no. 1, pp. 35-44, 2004.
30. [30] M. S. Hitam, W. N. J. H. W. Yussof, E. A. Awalludin, and Z. Bachok, “Mixture contrast limited adaptive histogram equalization for underwater image enhancement,” International conference on computer applications technology (ICCAT), 2013, pp. 1-5, Sousse, Tunisia.
31. [31] M. Kaur, R.K. Sarkar, and M.K. Dutta, “Investigation on quality enhancement of old and fragile artworks using non-linear filter and histogram equalization techniques,” Optik, vol. 244, no: 167564, 2021.
32. [32] O. A. Shawky, A. Hagag, E. S. A. E. Dahshan, and M. A. Ismail, “Remote sensing image scene classification using CNN-MLP with data augmentation,” Optik, vol. 221, no. 165356, 2020.
33. [33] R. Yan, J. Liao, J. Yang, W. Sun, M. Nong, and F. Li, “Multi-hour and multi-site air quality index forecasting in Beijing using CNN, LSTM, CNN-LSTM, and spatiotemporal clustering,” Expert Systems with Applications, vol. 169, no. 114513, 2021.
34. [34] W. Zhang, C. Li, G. Peng, Y. Chen, and Z. Zhang, “A deep convolutional neural network with new training methods for bearing fault diagnosis under noisy environment and different working load,” Mechanical Systems and Signal Processing, vol. 100, pp. 439-453, 2018.
35. [35] K. Fırıldak, ve M.F. Talu, “Evrişimsel Sinir Ağlarında Kullanılan Transfer Öğrenme Yaklaşımlarının İncelenmesi,” Computer Science, vol. 4, no. 2, pp. 88-95. 2019.
36. [36] V. Nair, and G.E. Hinton, “Rectified linear units improve restricted boltzmann machines,” 27th International Conference on Machine Learning (ICML-10), 2010, Haifa, Israel.
37. [37] K. Jarrett, K. Kavukcuoglu, M. A. Ranzato, and Y. LeCun, “What is the best multi-stage architecture for object recognition?,” 12th international conference on computer vision, 2009, pp. 2146-2153.
38. [38] N. B. Gaikwad, N. B. Gaıkwad, V. Tıwarı, A. Keskar, and N. C. Shıvaprakash, “Efficient FPGA implementation of multilayer perceptron for real-time human activity classification,” IEEE Access, vol. 7, pp. 26696-26706, 2019.
39. [39] J. Duchi, E. Hazan, and Y. Singer, “Adaptive subgradient methods for online learning and stochastic optimization,” Journal of machine learning research, vol. 12, no. 7, 2011.
40. [40] P. Flach, “Machine learning: the art and science of algorithms that make sense of data,” 2012: Cambridge University Press.
41. [41] R. T. Schirrmeister, J. T. Springenberg, L. D. J. Fiederer, M. Glasstetter, K. Eggensperger, M. Tangermann, F. Hutter, W. Burgard, and T. Ball, “Deep learning with convolutional neural networks for EEG decoding and visualization,” Human brain mapping, vol. 38, no. 11, pp. 5391-5420, 2017.
42. [42] I. Goodfellow, Y. Bengio, and A. Courville, “Deep learning,” 2016: MIT press.
43. [43] S. Ruder, “An overview of gradient descent optimization algorithms,” arXiv preprint arXiv:1609.04747, 2016.
44. [44] M. D. Zeiler, “Adadelta: an adaptive learning rate method,” arXiv preprint arXiv:1212.5701, 2012.
45. [45] D. P. Kingma, and J. Ba, “Adam: A method for stochastic optimization,” arXiv preprint arXiv:1412.6980, 2014.
46. [46] J. Jiao, M. Zhao, J. Lin, and K. Liang, “A comprehensive review on convolutional neural network in machine fault diagnosis,” Neurocomputing, vol. 417, pp. 36-63, 2020.