Recognition of Tongue Print Biometric using Oriented FAST and Rotated BRIEF (ORB)

The main goal of this study is to create a tongue print biometric system that utilizes the Oriented FAST and Rotated BRIEF (ORB) algorithm for feature extraction. The tongue print biometric system utilizes a Raspberry Pi as the microcontroller and acquires the image of tongue prints using a Raspberry Pi Camera with a Sony IMX219 8-megapixel sensor. The system initially captures the user’s tongue’s image and then uses the Contrast Limited Adaptive Histogram Equalization (CLAHE) for image pre-processing. Afterward, the ORB algorithm is used to extract the features on the Region of Interest, and then it computes the image descriptors. The descriptors are then stored in a database along with the user’s information. The data collection included thirty (30) authentic test subjects, where twenty (20) tongue prints were collected from the authentic users to train the prototype. After training, the system was tested five times on every authentic and impostor user, where the determined overall accuracy was 90.33%. Also, during the test on authentic users, the determined overall average recognition time speed of the tongue print biometric was 10.087 and the determined overall average recognition time speed when the biometric system was tested on an impostor was 10.1551 seconds. The integration of FAST and rBRIEF to ORB allowed the feature extraction algorithm to extract plenty of distributed feature points and load them fast, which led to the satisfactory accuracy rate and recognition time speeds of the tongue print biometric system.