Template Matching Algorithms in Palm Print Detection
Bernard Benedict R. Mendoza, Jerome Santiago, Jocelyn F. Villaverde · 2022
Biometrics is the study of the palm print, ridges, and patterns on the hand. It plays a significant role in our lives. It can be used for security, human recognition, and even in medicine. This research compared the six methods of Template Matching Algorithms on palm print detection; which are the Square Difference method, Correlation matching method, Normalized Cross-Correlation matching method, Correlation Coefficient matching method, Normalized Square Difference matching method, and Normalized Correlation Coefficient matching method. The six algorithms were each performed on the 20 samples. Then, a single-factor analysis of variance is performed to see if there are difference between the algorithms. The p-value of the single-factor analysis of variance is 0.760, which is higher than 0.05. This means that the group accepted the null of hypothesis that there is no difference between the 6 algorithms. The group conclude that all the Template Matching algorithms can be used to extract the palm which is region of interest for studies regarding palm print biometrics. The region of interest will be used for feature extraction. Upgrading the camera and performing a two-factor analysis of variance with background added as a factor can improve the study further.