Large Scale Face Clustering Based on Convolutional Neural Network

Shen Xiao-min; Li Bao-jun; Sun Xu; Xu Wei-chao

doi:10.3969/j.issn.1007-7162.2016.06.014

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

Large Scale Face Clustering Based on Convolutional Neural Network

更新时间：2026-05-27

- Large Scale Face Clustering Based on Convolutional Neural Network
- Vol. 33, Issue 6, Pages: 77-84(2016)
- 作者机构：
- 作者简介：
- 基金信息：
- DOI：10.3969/j.issn.1007-7162.2016.06.014
  CLC：
- Online First：18 November 2016，
  
  Published：2016
- 稿件说明：
移动端阅览
申小敏, 李保俊, 孙旭, 徐维超. 基于卷积神经网络的大规模人脸聚类[J]. 广东工业大学学报, 2016, 33(6): 77-84.

Shen Xiao-min, Li Bao-jun, Sun Xu, et al. Large Scale Face Clustering Based on Convolutional Neural Network[J]. 2016, 33(6): 77-84.
申小敏, 李保俊, 孙旭, 徐维超. 基于卷积神经网络的大规模人脸聚类[J]. 广东工业大学学报, 2016, 33(6): 77-84. DOI： 10.3969/j.issn.1007-7162.2016.06.014.

Shen Xiao-min, Li Bao-jun, Sun Xu, et al. Large Scale Face Clustering Based on Convolutional Neural Network[J]. 2016, 33(6): 77-84. DOI： 10.3969/j.issn.1007-7162.2016.06.014.

摘要

大规模人脸聚类不仅要求高效的人脸特征，还要求聚类算法在保持高准确率的同时耗时短.本文通过构建卷积神经网络高效提取人脸特征，并采用经典K-means算法和现阶段新颖的CFSFDP（Clustering by Fast Search and Find of Density Peaks）算法进行大规模人脸聚类.实验在聚类数目递增的情况下进行，并通过随机指标(Rand Index

RI)、信息熵、

-measure和混淆矩阵可视化来综合评估聚类的质量.结果表明，在大规模人脸聚类的情况下，卷积神经网络特征融合K-means的人脸聚类算法速度和准确率均优于CFSFDP算法.这一结论对大规模人脸聚类的实际应用具有重要的指导意义.

Abstract

The key challenge of large scale face clustering is to extract effective facial features and construct an accurate model with less time complexity. In this research

effective features are first extracted based on convolutional neural network (CNN). Then K-means

a classical cluster algorithm

and a state-of-art algorithm named CFSFDP (Clustering by Fast Search and Find of Density Peaks) are used to cluster large scale face images. Rand Index

entropy

-measure and the visualization of confusion matrix are further applied to comprehensively assess clustering quality. All the tests are under the condition of the increasing numbers of clustering centers. Experiment results demonstrate that K-means has a better performance as well as a much higher speed than CFSFDP. This

conclusion is believed to shed new light in the area of face clustering.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

A Multi-layer Convolutional Sparse Coding Network Based on Multi-Scale

An Insulator Burst Defect Detection Method Based on YOLOv4-MP

A Research on Deep Learning Object Detection Algorithm Based on Feature Fusion

A Review and Thinking of Deep Learning with a Restricted Number of Samples

A Lightweight Hyperspectral Remote Sensing Image Classification Method

Related Author

Zhang Jun

Xie Wei-li

Wen Gang

He Di-xuan

Lin Zhi-yi

Lin Li

Xie Guo-bo

Wang Zhen-you

Related Institution

School of Information Engineering, Guangdong University of Technology

School of Computer Science and Technology, Guangdong University of Technology

Yunnan Electric Power Research Institute, Yunnan Power Grid Co., Ltd

School of Applied Mathematics, Guangdong University of Technology

School of Automation, Guangdong University of Technology

AI问答

⁰