Sany., Rahma Juwita (2017) Penggunaan Ciri Geometric Invariant Moment Pada Pengenalan Tanda Tangan. Sarjana thesis, Universitas Brawijaya.
Abstract
Tanda tangan sebagai atribut personal merupakan salah satu wujud alat verifikasi identitas seseorang yang secara luas telah diterima oleh masyarakat. Proses pengenalan tanda tangan dimulai dari preprocessing, yang terdiri dari proses filtering, binerisasi, thinning, cropping dan resize. Setelah melakukan preprocessing dilanjutkan proses ekstraksi ciri menggunakan Geometric Invariant Moment untuk mendapatkan nilai fitur yang akan digunakan untuk proses klasifikasi menggunakan K-Nearest Neighbour. Variasi ciri Geometric Invariant Moment yang mempunyai nilai FAR dan FRR terkecil tiap sumber data berbeda. Untuk data dari Indonesia nilai FAR paling kecil didapatkan saat menggunakan moment 7 dengan nilai FAR=7% dan nilai FRR paling kecil didapatkan saat menggabungkan moment 1,2,3,6 dan 7 dan saat menggunakan semua moment dengan masing-masing mempunyai nilai FRR=61.5%. Untuk data dari Spanyol nilai FAR paling kecil didapatkan saat menggabungkan moment 3,4,5, dan 7, saat menggabungkan moment 1,3,4,5 dan 7 dan saat menggabungkan moment 1,3,4,5,6 dan 7 dengan masing-masing mendapatkan nilai FAR=7% dan nilai FRR paling kecil didapatkan dengan menggabungkan moment 2,3,4,5,6 dan 7 dan saat menggunakan semua moment dengan masing-masing mempunyai nilai FRR=72%. Untuk data dari Persia nilai FAR paling kecil didapatkan saat yaitu menggabungkan moment 3 dan 5 dan saat menggabungkan moment 3,5 dan 6 dengan masing-masing mempunyai nilai FAR=9.5% dan Persia nilai FRR paling kecil didapatkan saat menggabungkan moment 1,2,3,4,6 dan 7 dengan nilai FRR=37%. Ciri Geometric Invariant Moment yang diterapkan global pada suatu citra tidak memberikan akurasi yang tinggi. Mungkin karena ketika menerapkan ciri global, ciri lokal tidak terkenali dengan baik. Hal tersebut berlaku pada citra tanda tangan asli, sedangkan pada citra tanda tangan palsu penerapan ciri Geometric Invariant Moment secara global memberikan akurasi yang tinggi.
English Abstract
Signature as a personal attribute is one of the person’s identity verification equipment that is accepted widely by the society. The process of signature recognition starts from starts from preprocessing, which consist of filtering, thresholding, thinning, cropping and resizing. After preprocessing continued by feature extraction process using Geometric Invariant Moment to get the value of a feature that will be used for the classification process using K-Nearest Neighbour. The variations Geometric Invariant Moment feature that has the smallest of FAR value and FRR value on each data source are different. For data from Indonesia the smallest FAR obtained while using moment 7 with value is 7% and the smallest FRR obtained while combining moment 1,2,3,6 and 7 and using all of the moment with each value is 61.5%. For data from Spain the smallest FAR obtained while combining moment 3,4,5 and 7, moment 1,3,4,5 and 7 and combining 1,3,4,5,6 and 7 with each value is 7% and the smallest FRR obtained while combining moment 2,3,4,5,6 and 7 and using all of the moment with each value is 72%. For data from Persia the smallest FAR obtained while combining moment 3 and 5 and combining moment 3,5 and 6 with each value is 9.5% and the the smallest FRR obtained while combining moment 1,2,3,4,6 and 7 with value is 37%. The testing results of FAR and FRR is inversely proportional. The system can recoginize the fake signatures well that proven by getting FAR value is relatively small on all of data sources. But the system can’t recognize the original signatures well that proven by getting the high FRR value on all data sources. Features of Geometric Invariant Moment that applied globally on an image don't provide high accuracy. Perhaps, it happened because when apply global feature, the local features can’t recognize properly. It occurs on the original signature image, while the application of the features of Geometric Invariant globally on the fake signature image provide high accuracy.
| Item Type: | Thesis (Sarjana) |
|---|---|
| Identification Number: | SKR/FTIK/2017/241/051704815 |
| Uncontrolled Keywords: | pengenalan tanda tangan, Geometric Invariant Moment, K-Nearest Neighbour |
| Subjects: | 000 Computer science, information and general works > 006 Special computer methods > 006.4 Computer pattern recognition > 006.42 Optical pattern recognition > 006.425 Handwriting recognition |
| Divisions: | Fakultas Ilmu Komputer > Teknik Informatika |
| Depositing User: | Sugiantoro |
| Date Deposited: | 17 Jul 2017 02:45 |
| Last Modified: | 07 Sep 2020 06:36 |
| URI: | http://repository.ub.ac.id/id/eprint/271 |
![[thumbnail of 051704815 BAGIAN DEPAN.pdf]](http://repository.ub.ac.id/style/images/fileicons/text.png) |
Text
051704815 BAGIAN DEPAN.pdf Restricted to Repository staff only Download (111kB) |
|
Text
051704815 BAB I.pdf Restricted to Repository staff only Download (48kB) |
|
Text
051704815 BAB II.pdf Restricted to Repository staff only Download (120kB) |
|
Text
051704815 BAB III.pdf Restricted to Repository staff only Download (55kB) |
|
Text
051704815 BAB IV.pdf Restricted to Repository staff only Download (294kB) |
|
Text
051704815 BAB V.pdf Restricted to Repository staff only Download (146kB) |
|
Text
051704815 BAB VI.pdf Restricted to Repository staff only Download (350kB) |
|
Text
051704815 BAB VII.pdf Restricted to Repository staff only Download (40kB) |
|
Text
051704815 DAFTAR PUSTAKA.pdf Restricted to Repository staff only Download (38kB) |
Actions (login required)
 |
View Item |