篇名 |
Unrestricted Face Recognition Algorithm Based on Improved Residual Network IR-ResNet-SE
|
---|---|
並列篇名 | Unrestricted Face Recognition Algorithm Based on Improved Residual Network IR-ResNet-SE |
作者 | Hong-Rong Jing、Guo-Jun Lin、Tian-Tian Chen、Hong-Jie Zhang、Long Zhang、Shun-Yong Zhou |
英文摘要 | To solve the problem of poor face recognition performance in unrestricted environments. A face recognition algorithm based on improved residual IR-ResNet-SE is designed. Firstly, the IR structure is added to the 34-layer residual network to reduce the variability of different features; Secondly, we add the channel attention module to increase the weight of important channel features; Finally, the Arcface loss function is used to improve the classification ability of the model. The LFW, AgeDB, and AR datasets reflect unrestricted factors such as pose, age, expression, occlusion, and illumination. The algorithm proposed in this paper is experimented on these three datasets. The experimental results show that the IR-ResNet-SE algorithm proposed in this paper can achieve 99.74% accuracy in the dataset LFW. And it has excellent robustness in face recognition under unrestricted conditions.
|
起訖頁 | 029-039 |
關鍵詞 | residual network、SE attention、face recognition、Arcface |
刊名 | 電腦學刊 |
期數 | 202304 (34:2期) |
DOI |
|
QR Code | |
該期刊 上一篇
| Surface Defect Recognition of Wind Turbine Blades Based on Improved YOLOX-X Model |
該期刊 下一篇
| A Deep Reinforcement Learning-Based Approach in Porker Game |