VIE, GALANG RIZKY HANDIKA (2021) PERANCANGAN SISTEM PENGENALAN TELAPAK TANGAN TEKNOLOGI NIRSENTUH MENGGUNAKAN GRAY LEVEL CO-OCCURRENCE MATRIX DAN K-NEAREST NEIGHBOR. S1 thesis, Universitas Mercu Buana Jakarta.
|
Text (HAL COVER)
01 Cover.pdf Download (349kB) | Preview |
|
![[img]](https://repository.mercubuana.ac.id/style/images/fileicons/text.png) |
Text (BAB I)
02 Bab 1.pdf Restricted to Registered users only Download (62kB) |
|
|
Text (BAB II)
03 Bab 2.pdf Restricted to Registered users only Download (343kB) |
|
|
Text (BAB III)
04 Bab 3.pdf Restricted to Registered users only Download (160kB) |
|
|
Text (BAB IV)
05 Bab 4.pdf Restricted to Registered users only Download (343kB) |
|
|
Text (BAB V)
06 Bab 5.pdf Restricted to Registered users only Download (48kB) |
|
|
Text (DAFTAR PUSTAKA)
08 Daftar Pustaka .pdf Restricted to Registered users only Download (160kB) |
|
|
Text (LAMPIRAN)
09 Lampiran.pdf Restricted to Registered users only Download (1MB) |
Abstract
This study describes the design of a biometric system for touchless identification or identity verification through the human palmprint. The touchless palmprint recognition system can potentially be a good choice during the COVID-19 pandemic because the system can operate without touching the scanner so that it can reduce direct physical contact and can be applied in various identity. The system is designed using the Gray-Level Co-occurrence matrix (GLCM) feature extraction method to extract features. The identification recognition process in this study is divided into several stages, i.e, image acquisition, pre-processing, feature extraction with Gray-Level Co-occurrence matrix (GLCM), and matching with database using K-Nearest Neighbor (K-NN) classification. The system was tested using the 10-fold cross validation method with 100 sample images with 90 training images and 10 test images being tested alternately to calculate the average accuracy or system performance. Tests were carried out using each GLCM angle (0o, 45o, 90o and 135o) and K-NN with k values of 1, 5 and 7. The highest accuracy of the proposed method is 78% using 0o GLCM with k=1 and the lowest accuracy is 60% using 90o GLCM with k=7. Keywords: Palmprint recognition, Gray-Level Co-occurrence matrix, K-Nearest Neighbor, K-fold cross validation Penelitian ini menjelaskan desain sistem biometrik untuk identifikasi atau verifikasi identitas melalui telapak tangan manusia secara nirsentuh. Sistem pengenalan telapak tangan dapat berpotensi menjadi pilihan yang baik pada masa pandemi COVID-19 karena sistem dapat beroperasi tanpa menyentuh alat pemindai sehingga dapat mengurangi kontak fisik secara langsung dan dapat di aplikasikan di berbagai macam aplikasi pengenalan identitas. Sistem yang dirancang menggunakan metode ekstraksi fitur Gray-Level Co-occurrence matrix (GLCM) untuk mengekstraksi fitur. Dalam hal ini, proses identifikasi atau pengenalan dibagi dalam beberapa tahapan yaitu akuisisi citra, pre-processing, ekstraksi fitur dengan Gray-Level Co-occurrence matrix (GLCM) dan pencocokan dengan database menggunakan klasifikasi K-Nearest Neighbor (K-NN). Sistem diuji dengan menggunakan metode 10-fold cross validation dengan jumlah citra sample sebanyak 100 citra dengan 90 citra latih dan 10 citra uji yang di uji secara bergantian untuk menghitung rata-rata akurasi atau performansi sistem. Pengujian dilakukan dengan menggunakan setiap sudut GLCM (0o, 45o, 90o dan 135o) dan K-NN dengan nilai k 1, 5 dan 7. Tingkat akurasi tertinggi dari metode yang diusulkan sebesar 78% dengan menggunakan sudut 0o GLCM dan nilai k=1 dan tingkat akurasi terendah sebesar 60% pada sudut 90 o GLCM dan nilai k=7. Kata kunci: Pengenalan telapak tangan, Gray-Level Co-occurrence matrix, K-Nearest Neighbor, K-fold cross validation
Actions (login required)
 |
View Item |
