TY - JOUR TI - Fingerprints Image Recognition by Using Perceptron Artificial Neural Network AU - Muhammad Arif Budiman; I Gusti Agung Widagda IS - Vol 21 No 2 (2020): BULETIN FISIKA PB - Departement of Physics Faculty of Mathematics and Natural Sciences, and Institute of Research and Community Services Udayana University, Kampus Bukit Jimbaran Badung Bali JO - BULETIN FISIKA PY - 2020 SP - 37 EP - 46 UR - https://ojs.unud.ac.id/index.php/buletinfisika/article/view/58956/34588 AB - Security systems that use passwords or identity cards can be hacked and misused. One of alternative security system is to use biometric identification. The biometric system that is popularly used is fingerprints, because the system is safe and comfortable. Fingerprints have a distinctive pattern for each individual and this makes fingerprints relatively difficult to fake, so the system is safe. Comfortable because the verification process is easily done. The problem that often occurs on the system of fingerprint scanner is found an error and the user has difficulty when accessing. To handle with these problems has developed an artificial intelligence system. One of arificial intelligence in pattern identification is artificial neural networks (ANN). From some of the results of previous research showed that the ANN method is reliable in pattern identification. Based on these facts, the method used in this research is the perceptron ANN method with values learning rate varying. In the research the program conducted by testing 20 samples showed that the performance of the perceptron ANN method is relatively good method in fingerprint image recognition. This can be indicated from the value of accuracy (0.95), precision (0.83), TP rate (1), and FP rate (0.07)). In addition, the location of the point coordinate (FP rate; TP rate) is (0.07; 1) in ROC graphs is located on the upper left (perfect classifier region).