Samma, Hussein and Suandi, Shahrel Azmin and Mohamad Saleh, Junita (2022) A hybrid deep learning model for face sketch recognition. In: Proceedings of the 11th International Conference on Robotics, Vision, Signal Processing and Power Applications Enhancing Research and Innovation through the Fourth Industrial Revolution. Lecture Notes in Electrical Engineering, 829 (NA). Springer Science and Business Media Deutschland GmbH, Singapore, pp. 545-551. ISBN 978-981168128-8
Full text not available from this repository.
Official URL: http://dx.doi.org/10.1007/978-981-16-8129-5_83
Abstract
This paper introduces a hybrid deep learning model which integrates particle swarm optimization (PSO) with VGG-face deep learning network for face sketch recognition problem. Particularly, the proposed hybrid model incorporates PSO into VGG-face to find the best filters of the last layer that have the highest contribution in face sketch recognition. In addition, PSO performs fine-tuning for the selected filter to enhance recognition rate accuracy. To assess the performances of the proposed hybrid model, LFW face sketch benchmark images are used in this study. Reported results show that PSO can reduce VGG- face model complexity and increase recognition accuracy to 76% on LFW benchmark images.
| Item Type: | Book Section |
|---|---|
| Uncontrolled Keywords: | deep learning, face sketch recognition, particle swarm optimization, VGG-face |
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science |
| Divisions: | Computing |
| ID Code: | 100416 |
| Deposited By: | Yanti Mohd Shah |
| Deposited On: | 14 Apr 2023 01:25 |
| Last Modified: | 14 Apr 2023 01:25 |
Repository Staff Only: item control page
