Offline Signature Identification Using Deep Learning and Euclidean Distance
Hand signature is one of human characteristic that human have since birth, which can be used as identity recognition. A high accuracy signature recognition is needed to identify the right owner of signature. This study present signature identification using a combination method between Deep Learning...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | Indonesian |
| Published: |
Universitas Udayana
2021-08-01
|
| Series: | Lontar Komputer |
| Online Access: | https://ojs.unud.ac.id/index.php/lontar/article/view/73362 |
| Summary: | Hand signature is one of human characteristic that human have since birth, which can be used as identity recognition. A high accuracy signature recognition is needed to identify the right owner of signature. This study present signature identification using a combination method between Deep Learning and Euclidean Distance. 3 different signature datasets are used in this study which consist of SigComp2009, SigComp2011, and private dataset. Signature images preprocessed using binary image conversion, Region of Interest, and thinning. Several testing scenarios is applied to measure proposed method robustness, such as usage of various Pretrained Deep Learning, dataset augmentation, and dataset split ratio modifier. The best accuracy achieved is 99.44% with high precision rate. |
|---|---|
| ISSN: | 2088-1541 2541-5832 |