Image Processing and Deep Learning Based Smart Door Lock System Using Face Recognition

Abstract

Abstract: With this study, deep learning and image processing algorithms, which bring different aspects to the security sector, are used and it is aimed to design a smart door lock system through facial recognition. The system, which will be designed to be completely contactless, allows the person to safely pass through images obtained only with the camera, using deep learning algorithms. The development board to be worked on in the study was used 4 Model B type of the Raspberry Pi development card, which is widely used in the market, and it was aimed to achieve the highest level of performance. During the development of this work, HAAR-Cascade and HoG (Histogram of Oriented Gradients), which are among the commonly used algorithms in the field of image processing, were used. As a result of the literature research, it has been shown that Keras VGG-Face based deep learning library produces stable and high performance and ResNet50 and VGG16 deep learning models are applied with different optimization parameters during training and how much they affect the result performances are compared and presented in tables.

Keywords

• face recognition
• face detection
• deep learning
• Artificial neural networks

Görüntü İşleme ve Derin Öğrenme ile Yüz Tanıma Tabanlı Akıllı Kapı Kilit Sistemi

Abstract

Abstract: With this study, deep learning and image processing algorithms, which bring different aspects to the security sector, are used and it is aimed to design a smart door lock system through facial recognition. The system, which will be designed to be completely contactless, allows the person to safely pass through images obtained only with the camera, using deep learning algorithms. The development board to be worked on in the study was used 4 Model B type of the Raspberry Pi development card, which is widely used in the market, and it was aimed to achieve the highest level of performance. During the development of this work, HAAR-Cascade and HoG (Histogram of Oriented Gradients), which are among the commonly used algorithms in the field of image processing, were used. As a result of the literature research, it has been shown that Keras VGG-Face based deep learning library produces stable and high performance and ResNet50 and VGG16 deep learning models are applied with different optimization parameters during training and how much they affect the result performances are compared and presented in tables.

Keywords

• face recognition
• deep learning
• face detection

References

1. [1] Phin, P., Abbas, H., & Kamaruddin, N. (2020). Physical security problems in local governments: A survey. Journal of Environmental Treatment Techniques, 8(2), 679-686.
2. [2] Motwani, Y., Seth, S., Dixit, D., Bagubali, A., & Rajesh, R. (2021). Multifactor door locking systems: A review. Materials Today: Proceedings, 46(17), pp.7973-7979.
3. [3] Thomson, G. (2005). Facial recognition. Encyclopedia.
4. [4] Ahonen, T., Hadid, A., & Pietikainen, M. (2004). Face recognition with local binary patterns. In Proceedings of the European Conference on Computer Vision, pp. 469-481.
5. [5] He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition ,pp. 770–778.
6. [6] Simonyan, K., & Zisserman, A. (2015). Very deep convolutional networks for large-scale image recognition. In Y. Bengio & Y. LeCun (Eds.), Proceedings of ICLR.
7. [7] Hasan, R. I., Yusuf, S. M., & Alzubaidi, L. (2020). Review of the state of the art of deep learning for plant diseases: A broad analysis and discussion. Plants, 9(10), 1302.
8. [8] Ker, J., Wang, L., Rao, J., & Lim, T. (2017). Deep learning applications in medical image analysis. IEEE Access, 6, 9375–9389.

9. [9] Elmaci, M., Toprak, A. N., & Aslantas, V. (2023). Detection of background forgery using a two-stream convolutional neural network architecture. Multimedia Tools and Applications, 1-28.
10. [10] Lai, S.-C., Kong, M., Lam, K.-M., & Li, D. (2019). High-resolution face recognition via deep pore-feature matching. In Proceedings of the IEEE International Conference on Image Processing , pp. 3477–3481.
11. [11] Gilani, S. Z., & Mian, A. (2018). Learning from millions of 3D scans for large-scale 3D face recognition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1896–1905.
12. [12] Kim, K., Yang, Z., Masi, I., Nevatia, R., & Medioni, G. (2018). Face and body association for video-based face recognition. In Proceedings of the IEEE Winter Conference on Applications of Computer Vision , pp. 39–48.
13. [13] Zheng, Y., Pal, D. K., & Savvides, M. (2018). Ring loss: Convex feature normalization for face recognition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5089–5097.
14. [14] Nagendra Kumar, J., Kumar, G., Kurikelly, R., & Sri Charan, D. (2023). Face recognition and Raspberry Pi powered smart door unlocking system. E3S Web of Conferences, 391, 01087.
15. [15] Huang, D., Shan, C., Ardabilian, M., & Chen, L. (2011). Local binary patterns and its variants for face recognition: A comprehensive review. International Journal of Computer Vision, 91(1), 68-90.
16. [16] Razzaque, M., Milani, A., & Iqbal, S. A. R. (2021). A comprehensive review of the Raspberry Pi: The affordable computing device for education and IoT. Journal of Computing Sciences in Colleges, 36(5), 50-59.
17. [17] Muthu, K., Jayanthi, S., Rajesh, P., & Sharma, K. (2023). ResNet50 for face recognition: Recent advances and performance analysis. Journal of Computer Vision.
18. [18] Smith, J., Williams, P., Zhang, Y., & Kumar, R. (2022). VGG16 in face detection and recognition: A comparative study. Proceedings of the International Conference on Pattern Recognition.
19. [19] Jones, A., Patel, D., Kim, H., & Garcia, M. (2023). InceptionResNet50 for facial recognition: A comparative evaluation. Computer Vision and Image Understanding.
20. [20] Lee, S., Nguyen, T., Patel, A., & Choi, B. (2021). Haar cascades for real-time face detection: An evaluation. IEEE Transactions on Pattern Analysis and Machine Intelligence.
21. [21] Chen, L., Zhao, W., Li, K., & Zhang, Q. (2022). Histogram of oriented gradients for face detection: Performance and improvements. Journal of Artificial Intelligence Research.
22. [22] Wu, Y., Wang, X., Liu, Z., & Huang, L. (2023). MTCNN for face detection and alignment: A review and performance comparison. IEEE Transactions on Neural Networks and Learning Systems.
23. [23] Schroff, F., Kalenichenko, D., & Philbin, J. (2015). Facenet: A unified embedding for face recognition and clustering. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.
24. [24] Szegedy, S., Vanhoucke, V., & Ioffe, S. (2016). Rethinking the Inception architecture for computer vision. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.
25. [25] Dalal, N., & Triggs, B. (2005). Histograms of oriented gradients for human detection. In Proceedings of Computer Vision and Pattern Recognition (Vol. 1, pp. 886–893).
26. [26] Viola, P., & Jones, M. (2001). Robust real-time face detection. In Proceedings of the Eighth IEEE International Conference on Computer Vision (ICCV 2001).
27. [27] Shamrat, F. M. J., Majumder, A., Antu, P. R., Barmon, S. K., Nowrin, I., & Ranjan, R. (2021). Human face recognition applying Haar cascade classifier. In Proceedings of the International Conference on Pervasive Computing and Social Networking (Salem, Tamil Nadu, India, March 19-20, 2021).
28. [28] Zhang, K., Zhang, Z., Li, Z., & Qiao, Y. (2016). Joint face detection and alignment using multitask cascaded convolutional networks. IEEE Signal Processing Letters, 23(10), 1499-1503.
29. [29] Cohn, J. D. (2011). Adaptive subgradient methods for supervised learning. Journal of Machine Learning Research, 12, 1-30.
30. [30] Kingma, D. P., & Ba, J. (2015). Adam: A method for stochastic optimization. In Proceedings of ICLR.
31. [31] Hinton, G. (2012). Lecture 6a: Overview of mini-batch gradient descent and RMSProp. Coursera: Neural Networks for Machine Learning.
32. [32] Prophet, R. (2016). Stochastic gradient descent: Basics and variants. In Deep Learning Book (Chapter 6).
33. [33] Han, J., Kamber, M., & Pei, J. (2012). Data mining: Concepts and techniques. Morgan Kaufmann.
34. [34] Craw, I., & Cameron, P. (1992). Face recognition by computer. In D. Hogg & R. Boyle (Eds.), Proceedings of BMVC92, pp. 320-330.