[1]侯 青,杨荣新,张英杰,等.融合深度学习和聚类分析的自适应图像聚类[J].计算机技术与发展,2022,32(01):98-103.[doi:10. 3969 / j. issn. 1673-629X. 2022. 01. 017]
　HOU Qing,YANG Rong-xin,ZHANG Ying-jie,et al.Adaptive Image Clustering Integrating Deep Learning andClustering Analysis[J].,2022,32(01):98-103.[doi:10. 3969 / j. issn. 1673-629X. 2022. 01. 017]
点击复制

融合深度学习和聚类分析的自适应图像聚类()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
32
期数:
2022年01期
页码:
98-103
栏目:
图形与图像
出版日期:
2022-01-10

文章信息/Info

Title:
Adaptive Image Clustering Integrating Deep Learning andClustering Analysis
文章编号:
1673-629X(2022)01-0098-06
作者:
侯 青1 ; 杨荣新2 ; 张英杰2 ; 李 伟2
1. 陕西中医药大学 科技处,陕西 咸阳 712046;
2. 长安大学 信息工程学院,陕西 西安 710064
Author(s):
HOU Qing1 ; YANG Rong-xin2 ; ZHANG Ying-jie2 ; LI Wei2
1. Technology Department,Shaanxi University of Chinese Medicine,Xianyang 712046,China;
2. School of Information Engineering,Chang爷 an University,Xi爷 an 710064,China
关键词:
图像分类; 无监督; 融合; 自适应; AlexNet 网络; 快速峰值聚类
Keywords:
image classification; unsupervised; fusion; self-adaptation; AlexNet; fast peak clustering algorithm
分类号:
TP391. 4
DOI:
10. 3969 / j. issn. 1673-629X. 2022. 01. 017
摘要:
针对卷积神经网络应用于图像分类任务时需要大量有标签数据的问题,提出一种融合卷积神经网络和聚类分析的无监督分类模型,将无监督算法引入深度学习,并将该模型应用到图像分类领域,来弥补现有分类方式的不足。 首先对经典卷积神经网络 AlexNet 从网络结构和模型训练两个方面进行优化;然后利用改进后的自适应快速峰值聚类算法指导聚类过程,该模型在学习整个网络参数的同时对卷积输出的特征进行聚类,这两个过程迭代进行,以达到对图像进行无监督分类的目的;为了验证所提出的无监督图像分类模型的可行性和有效性,选用了四个常用于图像分类领域的数据集分别进行了分类实验,并将结果与近年来在图像无监督分类任务上表现相对优越的几种算法进行了横向对比。 结果表明提出的无监督分类模型在不同数据集上均较现有的几种无监督方法有着更出色的表现。
Abstract:
Aiming at the problem that a large amount of labeled data is required when the convolutional neural network is applied to imageclassification tasks,an unsupervised classification model combining convolutional neural network and cluster analysis is proposed. Theunsupervised algorithm is introduced into deep learning and the model is applied to image classification to make up for the shortcomingsof existing classification methods. Firstly,the classic convolutional neural network AlexNet is optimized in terms of network structure andmodel training. Then,the improved adaptive fast peak clustering algorithm is used to guide the clustering process. The model clusters thefeatures of the convolution output while learning the parameters of the entire network. These two processes are iterated to achieve thepurpose of unsupervised classification of images. Afterwards,in order to verify the feasibility and effectiveness of the unsupervised imageclassification model proposed, four data sets commonly used in the field of image classification are selected for the classificationexperiments,and the results are compared with the current performance on the image unsupervised classification task several relativelysuperior algorithms are compared horizontally. The comparative analysis proves that the unsupervised classification model proposed hasbetter performance than the existing unsupervised methods on different data sets.

相似文献/References:

[1]张江 王年 梁栋 唐俊.基于Laplace谱的图像分类[J].计算机技术与发展,2008,(05):73.
　ZHANG Jiang,WANG Nian,LIANG Dong,et al.Image Classification Based on Laplacian Spectra[J].,2008,(01):73.
[2]周伟 武港山.基于显著图的花卉图像分类算法研究[J].计算机技术与发展,2011,(11):15.
　ZHOU Wei,WU Gang-shan.Research on Saliency Map Based Flower Image Classification Algorithm[J].,2011,(01):15.
[3]李亚娥,汪西莉.一种自适应的半监督图像分类算法[J].计算机技术与发展,2013,(02):112.
　LI Ya-e,WANG Xi-li.An Adaptive Semi-supervised Image Classification Algorithm[J].,2013,(01):112.
[4]汪旗,贾兆红.基于多示例学习的图像分类算法[J].计算机技术与发展,2014,24(04):88.
　WANG Qi[],JIA Zhao-hong[].Image Categorization by Multi-instance Learning[J].,2014,24(01):88.
[5]武苏雯,赵慧杰,刘 鑫,等.基于迁移学习的图像分类在诗词中的应用研究[J].计算机技术与发展,2021,31(07):215.[doi:10. 3969 / j. issn. 1673-629X. 2021. 07. 036]
　WU Su-wen,ZHAO Hui-jie,LIU Xin,et al.Research on Application of Image Classification Based onTransfer Learning in Poetry[J].,2021,31(01):215.[doi:10. 3969 / j. issn. 1673-629X. 2021. 07. 036]
[6]阮航,孙涵.基于 Faster R-CNN 的车辆多属性识别[J].计算机技术与发展,2018,28(10):129.[doi:10.3969/ j. issn.1673-629X.2018.10.027]
　RUAN Hang,SUN Han.Vehicle Multi-attribute Recognition Based on Faster R-CNN[J].,2018,28(01):129.[doi:10.3969/ j. issn.1673-629X.2018.10.027]
[7]王 敏,陈立潮,曹建芳,等.Hadoop 下自适应随机权值多特征融合图像分类[J].计算机技术与发展,2018,28(11):30.[doi:10.3969/ j. issn.1673-629X.2018.11.007]
　WANG Min,CHEN Li-chao,CAO Jian-fang,et al.Multi-feature Fusion Image Classification of Adaptive Random Weight Based on Hadoop[J].,2018,28(01):30.[doi:10.3969/ j. issn.1673-629X.2018.11.007]
[8]阮航,王立春.基于特征图的车辆检测和分类[J].计算机技术与发展,2018,28(11):39.[doi:10.3969/ j. issn.1673-629X.2018.11.009]
　RUAN Hang,WANG Li-chun.Vehicle Detection and Classification Based on Feature Map[J].,2018,28(01):39.[doi:10.3969/ j. issn.1673-629X.2018.11.009]
[9]李一波,郭培宜,张森悦.深度卷积神经网络中激活函数的研究[J].计算机技术与发展,2021,31(09):61.[doi:10. 3969 / j. issn. 1673-629X. 2021. 09. 011]
　LI Yi-bo,GUO Pei-yi,ZHANG Sen-yue.Research on Activation Function in Deep Convolutional Neural Network[J].,2021,31(01):61.[doi:10. 3969 / j. issn. 1673-629X. 2021. 09. 011]
[10]宁秋怡,史小静,段湘煜.短语后验证的无监督领域适应电商机器翻译[J].计算机技术与发展,2021,31(12):1.[doi:10. 3969 / j. issn. 1673-629X. 2021. 12. 001]
　NING Qiu-yi,SHI Xiao-jing,DUAN Xiang-yu.Unsupervised Domain Adaptation E-commerce Machine Translation Based on Phrase Post-validation[J].,2021,31(01):1.[doi:10. 3969 / j. issn. 1673-629X. 2021. 12. 001]

更新日期/Last Update: 2022-01-10