JBJin Yeong Bok

Jin Yeong Bok

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Jin Yeong Bok has a total of 2 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Verifying the Effectiveness of New Face Spoofing DB with Capture Angle and Distance

    by Jin Yeong Bok, Kun Ha Suh, Eui Chul Lee

    Face recognition is a representative biometric that can be easily used; however, spoofing attacks threaten the security of face biometric systems by generating fake faces. Thus, it is not advisable to only consider sophisticated spoofing cases, such as three-dimensional masks, because they require additional equipment, thereby increasing the implementation cost. To prevent easy face spoofing attacks through print and display, the two-dimensional (2D) image analysis method using existing face recognition systems is reasonable. Therefore, we proposed a new database called the “pattern recognition-face spoofing advancement database” that can be used to prevent such attacks based on 2D image analysis. To the best of our knowledge, this is the first face spoofing database that considers the changes in both the angle and distance. Therefore, it can be used to train various positional relationships between a face and camera. We conducted various experiments to verify the efficiency of this database. The spoofing detection accuracy of our database using ResNet-18 was found to be 96.75%. The experimental results for various scenarios demonstrated that the spoof detection performances were better for images with pinch angle, near distance images, and replay attacks than those for front images, far distance images, and print attacks, respectively. In the cross-database verification result, the performance when tested with other databases (DBs) after training with our DB was better than the opposite. The results of cross-device verification in terms of camera type showed negligible difference; thus, it was concluded that the type of image sensor does not affect the detection accuracy. Consequently, it was confirmed that the proposed DB that considers various distances, capture angles, lighting conditions, and backgrounds can be used as a training DB to detect spoofing attacks in general face recognition systems.


  • Open Access

    Detecting Fake Finger-Vein Data Using Remote Photoplethysmography

    by Jin Yeong Bok, Kun Ha Suh, Eui Chul Lee

    Today, biometrics is being widely used in various fields. Finger-vein is a type of biometric information and is based on finger-vein patterns unique to each individual. Various spoofing attacks have recently become a threat to biometric systems. A spoofing attack is defined as an unauthorized user attempting to deceive a system by presenting fake samples of registered biometric information. Generally, finger-vein recognition, using blood vessel characteristics inside the skin, is known to be more difficult when producing counterfeit samples than other biometrics, but several spoofing attacks have still been reported. To prevent spoofing attacks, conventional finger-vein recognition systems mainly use the difference in texture information between real and fake images, but such information may appear different depending on the camera. Therefore, we propose a method that can detect forged finger-vein independently of a camera by using remote photoplethysmography. Our main idea is to get the vital sign of arterial blood flow, a biometric measure indicating life. In this paper, we selected the frequency spectrum of time domain signal obtained from a video, as the feature, and then classified data as real or fake using the support vector machine classifier. Consequently, the accuracy of the experimental result was about 96.46%.