Segmentation Method for Face Modelling in Thermal Images
| Autor: | Albar Albar, Hendrick Hendrick, Rahmad Hidayat |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: | |
| Zdroj: | Knowledge Engineering and Data Science, Vol 3, Iss 2, Pp 99-105 (2020) |
| Druh dokumentu: | article |
| ISSN: | 2597-4602 2597-4637 |
| DOI: | 10.17977/um018v3i22020p99-105 |
| Popis: | Face detection is mostly applied in RGB images. The object detection usually applied the Deep Learning method for model creation. One method face spoofing is by using a thermal camera. The famous object detection methods are Yolo, Fast RCNN, Faster RCNN, SSD, and Mask RCNN. We proposed a segmentation Mask RCNN method to create a face model from thermal images. This model was able to locate the face area in images. The dataset was established using 1600 images. The images were created from direct capturing and collecting from the online dataset. The Mask RCNN was configured to train with 5 epochs and 131 iterations. The final model predicted and located the face correctly using the test image. |
| Databáze: | Directory of Open Access Journals |
| Externí odkaz: |
|