AbstrakTanda tangan merupakan salah satu biometrik pada karakteristik perilaku yang digunakan untuk mengenali seseorang sebagai sistem identifikasi. Fungsi tanda tangan adalah untuk menentukan kebenaran ciri-ciri dari penandatangan atau diperlukan untuk memastikan identifikasi seseorang yang valid. Meskipun unik, banyak terjadi kasus tanda tangan yang disalahgunakan dengan cara dipalsukan. Tidak mudah mengenali tanda tangan yang palsu dengan tanda tangan asli. Untuk itu, diperlukan mekanisme pengenalan tanda tangan ini dengan suatu algoritma. Proses pengenalan tanda tangan bisa dilakukan secara statik (offline) maupun dinamik (online). Penelitian ini dilakukan berdasarkan pengenalan secara offline, yang dikenal lebih sulit daripada pengenalan secara online. Algoritma yang dilibatkan meliputi Learning Vector Quantization, deteksi tepi Sobel, dan ekstraksi fitur Local Binary Pattern untuk mengidentifikasi tanda tangan. Hasil penelitian menunjukkan, jumlah data citra, iterasi, dan learning rate mempengaruhi akurasi dan waktu proses identifikasi. Dari percobaan yang dilakukan pada parameter yang berbeda-beda, akurasi yang didapat adalah 68% pada data latih dan pada data uji sebesar 54,6%. AbstractA signature is one of the biometrics on behavioral characteristics used to recognize a person as an identification system. The function of the signature is to determine the correctness of the characteristics of the signatory or is needed to ensure valid identification of a person. Although unique, there are many cases of signatures that are misused by falsification. It is not easy to recognize a fake signature with an original signature. For this reason, this signature recognition mechanism is needed with an algorithm. The signature recognition process can be done either statically (offline) or dynamically (online). This research is based on offline recognition, which is known to be more difficult than online recognition. The algorithms involved include Learning Vector Quantization, Sobel edge detection, and Local Binary Pattern feature extraction to identify signatures. The results showed, the amount of image data, iteration, and learning rate affect the accuracy and time of the identification process. From experiments conducted on different parameters, the accuracy obtained was 68% in the training data and in the test data at 54.6%.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.