Abstract—Generally, the process of verifying a person’s identification in a bank is accomplished by an officer comparing a photo in an ID card with the actual face of the person. This process is prone to mistake as officers usually need to serve several people in a short time. This article proposes the personal verification system using an ID card and face photo by applying face detection and face comparison. A system based on several open source libraries for face recognition including Dlib, Facenet, and ArcFace is implemented. The experimental analysis shows that the system based on ArcFace yields the highest accuracy at 99.06% for face detection and 96.09% for face comparison. ArcFace outperforms other methods because it not only uses MTCNN but also adjusts face image to be in a straight direction as well as fixes the positions of eyebrows, eyes nose, and mouth so that all images have similar references.
Index Terms—Face comparison, face detection.
Adulwit Chinapas, Pattarawit Polpinit, and Kanda Runapongsa Saikaew are with the Faculty of Engineering, Khon Kaen University, Thailand (Corresponding author; e-mail: email@example.com).
Cite: Adulwit Chinapas, Pattarawit Polpinit, Narong Intiruk, and Kanda Runapongsa Saikaew, "Personal Verification System Using ID Card and Face Photo," International Journal of Machine Learning and Computing vol. 9, no. 4, pp. 407-412, 2019.Copyright © 2019 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).