Face Shape Classification Based on Bilinear Network with Attention Mechanism

Face Shape Classification Based on Bilinear Network with Attention Mechanism
复制标题

基于带有注意力机制的双线性网络的人脸形状分类

DOI:
10.1088/1742-6596/2278/1/012041
复制
发表时间:
2022-05
期刊:
IOP Publishing
影响因子:
--
通讯作者:
Longsheng Xie
Longsheng Xie
中科院分区:
其他
文献类型:
--
作者:
Jiawei Duan;Xueping Su;Jie Ren;Longsheng Xie

文献摘要

参考文献

相似文献

摘要人脸形状是人脸识别、个性化推荐等应用中的重要信息。例如,在人脸识别之前对人脸进行粗略的形状过滤,可以有效地提高识别的准确率和速度。同时,可以使用有效的人脸形状分类来构建发型和眼镜推荐系统。因此,本文提出了一种新的人脸形状分类算法。首先,提出了基于M-RetinaFace网络的人脸图像对齐方法。其次,将注意力机制与EfficientNet双线性网络相结合,提出了AB-CNN网络进行特征提取。最后,使用双线性汇聚层对人脸形状进行分类。在公开数据集上的实验表明,与现有算法相比,本文提出的算法获得了最先进的结果,显著提高了人脸形状分类的准确率。
Abstract Face shape is an important information in face recognition, personalized recommendation and other applications. For example, rough face shape filtering before face recognition can effectively improve the recognition accuracy and speed. At the same time, an effective face shape classification can be used to construct a recommendation system for hairstyles and glasses. Therefore, this paper proposes a new face shape classification algorithm. Firstly, the M-RetinaFace network is proposed to align face image. Secondly, by combing the attention mechanism with the EfficientNet bilinear network, the AB-CNN network is proposed to extract feature. Finally, a bilinear pooling layer is used to classify face shape. Experiments on public data sets show that, compared with existing algorithms, the algorithm proposed in this paper is get state-of-the-art results and significantly improves the accuracy of face shape classification.
DOI: 10.1109/icce.2014.6776105
发表时间: 2014
期刊: 2014 IEEE International Conference on Consumer Electronics (ICCE)
影响因子: --
作者:
Wan-Yu Chen;Jia-Lin Chen;Liang-Gee Chen
通讯作者: Wan-Yu Chen;Jia-Lin Chen;Liang-Gee Chen
DOI: --
发表时间: 2011
期刊: Computer Engineering
影响因子: --
作者:
Tu Yi
通讯作者: Tu Yi
DOI: --
发表时间: 2021
期刊: Agronomy
影响因子: --
作者:
通讯作者: --
DOI: 10.1016/j.eswa.2018.11.011
发表时间: 2019-04
期刊: Expert Syst. Appl.
影响因子: --
作者:
Kitsuchart Pasupa;Wisuwat Sunhem;C. Loo
通讯作者: Kitsuchart Pasupa;Wisuwat Sunhem;C. Loo
DOI: --
发表时间: 2013
期刊: --
影响因子: --
作者:
Lu Li;Jaehun Soo;Hyun-Chool Shin;Youngjoon Han
通讯作者: Lu Li;Jaehun Soo;Hyun-Chool Shin;Youngjoon Han