Identification with Face Recognition Methods in Real Life Applications

Abstract

The development of technologies such as employment tracking systems, personal security, and the use of robots has led a lot of studies on face recognition systems. In the most of studies considering face recognition, recognition accuracies are very high, since training and testing images are selected randomly from the same databases. However, in real life applications, these images are not randomly selected from the same database. Because, these systems are trained during installation of the recognition system or when a new person needs to be introduced to the system. On the other hand, images used for predictions are uploaded to the system at other times. In this study, it is aimed to show that the accuracy rates of real-life face recognition systems differ from the systems trained and tested with randomly selected images as usually done in literature. To observe this difference in the first step, training and test images are selected randomly. In the second step, training and test images are divided according to the recording dates as in real life. Accuracy rates are evaluated by using linear discriminant analysis, local binary patterns and principal component analysis methods. Although the accuracies are very high for the first step, it is seen that the accuracies fell dramatically in the second step for all methods. Afterwards a new method is searched also in this study to increase these low accuracy rates. It is shown that usage of eye area images instead of face images has higher accuracy rates in all above methods for real life applications.

Keywords

• Eye Area Recognition
• OpenCv
• Image Processing
• Linear Discriminant Analysis
• Local Binary Patterns
• Principal Component Analysis
• Face Recognition

References

1. Li, X. and Zhang, H. (2013, March). A survey of face recognition methods. In Proceedings of the 2nd International Conference on Computer Science and Electronics Engineering. Atlantis Press
2. Deng, W., Hu, J., Guo, J., Cai, W. and Feng, D. (2010). Robust, accurate and efficient face recognition from a single training image: A uniform pursuit approach. Pattern Recognition, 43(5): 1748-1762.
3. Lee, H. S., Park, S., Kang, B. N., Shin, J., Lee, J. Y., Je, H. and Kim, D. (2008, September). The POSTECH face database (PF07) and performance evaluation. In 2008 8th IEEE International Conference on Automatic Face & Gesture Recognition (pp. 1-6). IEEE.
4. Boyko, N., Basystiuk, O. and Shakhovska, N. (2018, August). Performance evaluation and comparison of software for face recognition, based on dlib and opencv library. In 2018 IEEE Second International Conference on Data Stream Mining & Processing (DSMP) (pp. 478-482). IEEE.
5. Memiş, A. and Karabiber, F. (2016, May). Face recognition on mobile environment images using appearance based methods. In 2016 24th Signal Processing and Communication Application Conference (SIU) (pp. 169-172). IEEE.
6. Abdulsamet, H. and Olcay, T. (2017, October). Identification system from motion pictures: LBPH application. In 2017 International Conference on Computer Science and Engineering (UBMK) (pp. 845-850). IEEE.
7. Ayata, F., Çavuş, H., İnan, M., Seyyarer, E., Biçek, E., & Kina, E. (2020). Dostroajan: Facial Recognition Based System Input Control Agent. AJIT-e, 11(40), 82.
8. Aksoy, B. (2019). Yüz Tanima Sistemlerinde Doğruluk Performanslarinin Değerlendirilmesi. Mühendislik Bilimleri ve Tasarım Dergisi, 7(4), 835-842.

9. He, X., Yan, S., Hu, Y., Niyogi, P., & Zhang, H. J. (2005). Face recognition using laplacianfaces. IEEE transactions on pattern analysis and machine intelligence, 27(3), 328-340.
10. Ünal, F. Z. (2019). A Comparison Of Deep Learning Based Architecture With A Conventional Approach For Face Recognition Problem. Communications Faculty of Sciences University of Ankara Series A2-A3 Physical Sciences and Engineering, 61(2), 129-149.
11. Turk, M. and Pentland, A. (1991, January). Face recognition using eigenfaces. In Proceedings. 1991 IEEE computer society conference on computer vision and pattern recognition (pp. 586-587).
12. Belhumeur, P. N., Hespanha, J. P. and Kriegman, D. J. (1997). Eigenfaces vs. fisherfaces: Recognition using class specific linear projection. IEEE Transactions on pattern analysis and machine intelligence, 19(7): 711-720.
13. Kaçar, Ü., Kirci, M., Güneş, E. O. and İnan, T. (2015, May). A comparison of PCA, LDA and DCVA in ear biometrics classification using SVM. In 2015 23nd Signal Processing and Communications Applications Conference (SIU) (pp. 1260-1263). IEEE.
14. Yang, J., Yu, H., & Kunz, W. (2000, December). An efficient LDA algorithm for face recognition. In Proceedings of the International Conference on Automation, Robotics, and Computer Vision (ICARCV 2000) (pp. 34-47).
15. Jain, U., Choudhary, K., Gupta, S. and Privadarsini, M. J. P. (2018, May). Analysis of Face Detection and Recognition Algorithms Using Viola Jones Algorithm with PCA and LDA. In 2018 2nd International Conference on Trends in Electronics and Informatics (ICOEI) (pp. 945-950). IEEE.
16. Ahonen, T., Hadid, A. and Pietikainen, M. (2006). Face description with local binary patterns: Application to face recognition. IEEE transactions on pattern analysis and machine intelligence, 28(12): 2037-2041.
17. Viola, P., & Jones, M. (2001, December). Rapid object detection using a boosted cascade of simple features. In Proceedings of the 2001 IEEE computer society conference on computer vision and pattern recognition. CVPR 2001 (Vol. 1, pp. I-I). IEE.
18. Ediz, Ç,. (2020). Adding Virtual Objects to Realtime Images; A Case Study in Augmented Reality. Sakarya University Journal of Computer and Information Sciences, 3(3), 188-200.