[1]于 全,宋金玉,余晓晗.解决抽象标签的图像分类的多示例两阶段模型[J].计算机技术与发展,2022,32(06):68-73.[doi:10. 3969 / j. issn. 1673-629X. 2022. 06. 012]
　YU Quan,SONG Jin-yu,YU Xiao-han.Multi-instance Two-stage Model of Solving Image Classification Problem of Abstract Labels[J].,2022,32(06):68-73.[doi:10. 3969 / j. issn. 1673-629X. 2022. 06. 012]
点击复制

解决抽象标签的图像分类的多示例两阶段模型()

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

卷:
32
期数:
2022年06期
页码:
68-73
栏目:
图形与图像
出版日期:
2022-06-10

文章信息/Info

Title:
Multi-instance Two-stage Model of Solving Image Classification Problem of Abstract Labels
文章编号:
1673-629X(2022)06-0068-06
作者:
于 全; 宋金玉; 余晓晗
陆军工程大学 指挥控制工程学院,江苏 南京 210007
Author(s):
YU Quan; SONG Jin-yu; YU Xiao-han
School of Command & Control Engineering,Army Engineering University of PLA,Nanjing 210007,China
关键词:
多示例学习; 图像分类; 抽象标签; Yolo; 多层感知机
Keywords:
multi-instance learning; image classification; abstract labels; Yolo; multilayer perceptron
分类号:
TP31
DOI:
10. 3969 / j. issn. 1673-629X. 2022. 06. 012
摘要:
经过训练的分类模型可以准确识别出图像中的具体对象,找出“ 图像中有什么” ,但针对诸如“图片描述了什么” 的抽象概念标签的图像分类问题研究较少,研究难度也更大。 抽象概念标签不属于图像中包含的任何一个具体的对象,而是由许多不同的概念混合在一起,所以直接学习这个抽象标签相当困难。 为了解决这类抽象标签的图像分类问题,借助多示例学习方法思路,设计并实现了多示例两阶段模型。 该模型由两个阶段构成,第一阶段基于 Yolo 模型修改,实现从图像中快速、精准提取出具体对象,第二阶段构建多层感知机,利用第一阶段模型的结果最终得到图像的分类抽象概念。 最后,通过一个具有示范性的实验案例,验证多示例两阶段模型可以利用多示例学习有效解决抽象标签的图像分类问题,展示了多示例两阶段模型的可行性。
Abstract:
The trained classification model can accurately identify the specific objects in the image and find out “ what is in the image” .However,there are few researches on the image classification of abstract concept labels such as “ what is described in the image” ,and theresearch is more difficult. The abstract concept label does not belong to any one concrete object contained in the image,but is a mixtureof many different concepts,so it is quite difficult to learn this abstract label directly. In order to solve the problem of image classificationof such abstract labels,with the help of multi - instance learning method,we design and implement a multi - instance two - stage modelwhich consists of two stages. The first-stage is based on the modification of Yolo model to extract the concrete object from the imagequickly and accurately,and the second stage is to build multi - layer perceptron and finally obtain the classification abstract concept ofimages using the results of the first-stage model. Finally,through a demonstrative experimental case,it is verified that the multi-instancetwo-stage model can effectively solve the image classification problem of abstract labels by using multi - instance learning, and thefeasibility of the multi-instance two-stage model is demonstrated.

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,(06):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,(06):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,(06):112.
[4]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(06):215.[doi:10. 3969 / j. issn. 1673-629X. 2021. 07. 036]
[5]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(06):129.[doi:10.3969/ j. issn.1673-629X.2018.10.027]
[6]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(06):30.[doi:10.3969/ j. issn.1673-629X.2018.11.007]
[7]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(06):39.[doi:10.3969/ j. issn.1673-629X.2018.11.009]
[8]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(06):61.[doi:10. 3969 / j. issn. 1673-629X. 2021. 09. 011]
[9]陈玉红,刘晓静*.基于卷积神经网络的唐卡尊像自动分类研究[J].计算机技术与发展,2021,31(12):167.[doi:10. 3969 / j. issn. 1673-629X. 2021. 12. 028]
　CHEN Yu-hong,LIU Xiao-jing*.Research on Automatic Classification of Thangka Images Based on Convolutional Neural Network[J].,2021,31(06):167.[doi:10. 3969 / j. issn. 1673-629X. 2021. 12. 028]
[10]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.[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(06):98.[doi:10. 3969 / j. issn. 1673-629X. 2022. 01. 017]
[11]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(06):88.

更新日期/Last Update: 2022-06-10