| 稀疏特征重用的人脸特征提取网络 |
| |
| 引用本文： | 胡超,李春国,杨绿溪. 稀疏特征重用的人脸特征提取网络[J]. 信号处理, 2021, 37(7): 1153-1163. DOI: 10.16798/j.issn.1003-0530.2021.07.004 |
| |
| 作者姓名： | 胡超 李春国 杨绿溪 |
| |
| 作者单位： | 东南大学信息科学与工程学院 |
| |
| 基金项目： | 国家自然科学基金（61671144，U1936201，61971128，61941115） |
| |
| 摘 要： | 为了提高人脸特征提取网络的性能,进而提高人脸识别算法的准确率,本文对基于卷积神经网络的人脸特征提取网络进行研究,提出了 SFRNet(Sparse Feature Reuse Network).首先,基于稀疏特征重用、混合特征融合、中心-高斯池化三个创新点,给出了 SFRNet的网络结构.然后,在图像分类数据集Imag...
|
| 关 键 词： | 特征提取 人脸识别 卷积神经网络 特征重用 |
| 收稿时间： | 2021-02-02 |
Face Feature Extraction Network Based on Sparse Feature Reuse |
| |
| Affiliation: | School of Information Science and Engineering, Southeast University |
| |
| Abstract: | In order to improve the performance of the face feature extraction network and then the accuracy of the face recognition algorithm, this paper studies the network of the face feature extractor based on the convolutional neural network and proposes SFRNet (Sparse Feature Reuse Network). First, based on the three innovations of sparse feature reuse, hybrid feature fusion, and Center-Gaussian pooling, the network structure of SFRNet is given. Then, experiments were performed on the image classification dataset ImageNet, the face recognition dataset LFW (Labeled Faces in the Wild), and MegaFace, respectively, to verify the feature extraction capabilities of SFRNet in the general scene and the specific scene of face recognition. Experiments show that the SFRNet designed in this article not only has a small amount of calculation and parameters, but also can effectively extract facial features and has strong generalization ability in general scenes. |
| |
| Keywords: | |
|
| 点击此处可从《信号处理》浏览原始摘要信息 |
|
点击此处可从《信号处理》下载免费的PDF全文 |
|
