Improvement Palmprint Recognition System by Adjusting Image Data Reference Points

Abstract

Nowadays, the palmprint recognition method is an attractive tool for people recognition besides face recognition and fingerprint. To get a good palmprint recognition system requires a series of algorithms that are united and worked together to create a preferred method. The biometric system in palmprint recognition is said to be preferred when the choice of the algorithm applied has the advantage of each phase. Generally, The palmprint recognition system starts from the selection of image filters, image positioning, dimension reduction, and finally, end with the distance method. Image normalization position is a problem for researchers because the palmprint is always moving and shows a curved shape making it difficult for the system in the identification and verification process. For this reason, the research focuses on the selection of orientation scale operator value from the Gabor technique to get the best parameter value for palmprint biometrics. The desired system is when the overall performance of the algorithm used will produce an output with a low EER value and a high level of verification. From the research that has been carried out, the range of 8 × 5 becomes a good alternative for the choice of Gabor value pairs.