基于集成分类的暴恐图像自动标注方法

严靓; 周欣; 何小海; 熊淑华; 卿粼波

doi:doi:10.11805/tkyda2019157

太赫兹科学与电子信息学报, 2020, 18 (2): 306, 网络出版: 2020-05-28

基于集成分类的暴恐图像自动标注方法

Violent image annotation using ensemble learning

论文大纲

严靓周欣何小海 ^*熊淑华卿粼波

作者单位

四川大学电子信息学院，四川成都 610065

图像标注多标签分类集成学习权重分配样本不均衡 image annotation multi-label classification ensemble learning weight allocation label category imbalance

摘要

为减少暴恐图像对社会发展和青少年成长造成的不利影响，本文提出一种基于集成分类的暴恐图像自动标注方法，辅助筛除网页中的暴恐信息。该方法将暴恐图像的标注视作多标签分类问题，利用迁移学习训练多个子网络，然后通过集成学习对子网络的输出进行融合，同时在融合过程中针对各个标签在不同网络上的准确率进行权重分配，最后经过一系列矩阵运算得到图像的标注结果。实验结果表明，与传统机器学习算法相比，本文方法在准确率和召回率上都有较大提升，并改善了样本不均衡所造成的不同标签类别上模型标注精确度差异较大的问题。

Abstract

In order to reduce the negative impact of the horror image on social development and adolescent growth, a violent image annotation algorithm based on ensemble learning is proposed, assisting in screening out the horror information in the webpage. The annotation of violent image is considered as a multi-label classification problem in this method. Multiple sub-networks are trained through transfer learning, and then the ensemble learning is introduced to fuse the outputs of sub-networks. In the process of fusion, weights are allocated according to the precision of each label on different networks, thus the annotation result is obtained through a series of matrix operations. The experimental results show that the proposed method achieves a great improvement in precision and recall than traditional machine learning algorithm, and also improves the problem that the precision of model annotation on different labels varies greatly due to the label category imbalance.

参考文献

[1] 徐勇,张慧. 图像自动标注方法研究综述[J]. 现代情报, 2016,36(3):144-150. (XU Yong,ZHANG Hui. Summary of automatic image annotation method[J]. Journal of Modern Information, 2016,36

徐勇,张慧. 图像自动标注方法研究综述[J]. 现代情报, 2016,36(3):144-150. (XU Yong,ZHANG Hui. Summary of automatic image annotation method[J]. Journal of Modern Information, 2016,36 (3):144-150.)

(3):144-150.)

[2] 刘凯,张立民,孙永威,等. 利用深度玻尔兹曼机与典型相关分析的自动图像标注算法[J]. 西安交通大学学报, 2015, 49(6):33-38. (LIU Kai,ZHANG Limin,SUN Yongwei,et al. An automatic image annotation algorithm using deep Boltzmann machine and canonical correlation analysis[J]. Journal of Xi’an Jiaotong University, 2015,49(6):33-38.)

刘凯,张立民,孙永威,等. 利用深度玻尔兹曼机与典型相关分析的自动图像标注算法[J]. 西安交通大学学报, 2015, 49(6):33-38. (LIU Kai,ZHANG Limin,SUN Yongwei,et al. An automatic image annotation algorithm using deep Boltzmann machine and canonical correlation analysis[J]. Journal of Xi’an Jiaotong University, 2015,49(6):33-38.)

刘凯,张立民,孙永威,等. 利用深度玻尔兹曼机与典型相关分析的自动图像标注算法[J]. 西安交通大学学报, 2015, 49(6):33-38. (LIU Kai,ZHANG Limin,SUN Yongwei,et al. An automatic image

annotation algorithm using deep Boltzmann machine and canonical correlation analysis[J]. Journal of Xi’an Jiaotong University, 2015,49(6):33-38.)

[3] Knowledge Technology. Urmia,Iran:IEEE, 2015:1-7.

MAJIDPOUR J,KHEZRI E,HASSANZADE H,et al. Interactive tool to improve the automatic image annotation using MPEG-7 and multi-class SVM[C]// IEEE Conference on Information and Knowledge Technology. Urmia,Iran:IEEE, 2015:1-7.

MAJIDPOUR J,KHEZRI E,HASSANZADE H,et al. Interactive tool to improve the automatic image annotation using MPEG-7 and multi-class SVM[C]// IEEE Conference on Information and

[4] machine[J]. Applied Intelligence, 2018,48(1):166-181.

MEHMOOD Z,MAHMOOD T,JAVID M A. Content-based image retrieval and semantic automatic image annotation based on the weighted average of triangular histograms using support vector

MEHMOOD Z,MAHMOOD T,JAVID M A. Content-based image retrieval and semantic automatic image annotation based on the weighted average of triangular histograms using support vector machine[J]. Applied Intelligence, 2018,48(1):166-181.

[5] JI Q,ZHANG L,LI Z. KNN-based image annotation by collectively mining visual and semantic similarities[J]. KSII Transactions on Internet & Information Systems, 2017,11(9):4476-4490.

JI Q,ZHANG L,LI Z. KNN-based image annotation by collectively mining visual and semantic similarities[J]. KSII Transactions on Internet & Information Systems, 2017,11(9):4476-4490.

[6] SU F,XUE L. Graph learning on K nearest neighbors for automatic image annotation[C]// Proceedings of the 5th ACM on International Conference on Multimedia Retrieval. Shanghai,China:ACM, 2015:403-410.

SU F,XUE L. Graph learning on K nearest neighbors for automatic image annotation[C]// Proceedings of the 5th ACM on International Conference on Multimedia Retrieval. Shanghai,China:ACM, 2015:403-410.

SU F,XUE L. Graph learning on K nearest neighbors for automatic image annotation[C]// Proceedings of the 5th ACM on International Conference on Multimedia Retrieval.

Shanghai,China:ACM, 2015:403-410.

[7] ZHANG W,HU H,HU H. Training visual-semantic embedding network for boosting automatic image annotation[J]. Neural Processing Letters, 2018,48(3):1503-1519.

ZHANG W,HU H,HU H. Training visual-semantic embedding network for boosting automatic image annotation[J]. Neural Processing Letters, 2018,48(3):1503-1519.

[8] 张华忠,侯进. 基于决策树C4.5集成算法的图像自动标注[J]. 计算机应用研究, 2018,321(7):308-310. (ZHANG Huazhong,HOU Jin. Image annotation based on decision tree C4.5 ensemble algorithm

张华忠,侯进. 基于决策树C4.5集成算法的图像自动标注[J]. 计算机应用研究, 2018,321(7):308-310. (ZHANG Huazhong,HOU Jin. Image annotation based on decision tree C4.5 ensemble algorithm [J]. Application Research of Computers, 2018,321(7):308-310.)

[J]. Application Research of Computers, 2018,321(7):308-310.)

[9] FAKHARI A,MOGHADAM A M E. Combination of classification and regression in decision tree for multi-labeling image annotation and retrieval[J]. Applied Soft Computing, 2013,13 (2):1292-1302.

FAKHARI A,MOGHADAM A M E. Combination of classification and regression in decision tree for multi-labeling image annotation and retrieval[J]. Applied Soft Computing, 2013,13 (2):1292-1302.

(2):1292-1302.

FAKHARI A,MOGHADAM A M E. Combination of classification and regression in decision tree for multi-labeling image annotation and retrieval[J]. Applied Soft Computing, 2013,13

[10] (2):674-683.

RAJCHL M,LEE M,OKTAY O,et al. Deep cut: object segmentation from bounding box annotations using convolutional neural networks[J]. IEEE Transactions on Medical Imaging, 2017,36

RAJCHL M,LEE M,OKTAY O,et al. Deep cut: object segmentation from bounding box annotations using convolutional neural networks[J]. IEEE Transactions on Medical Imaging, 2017,36 (2):674-683.

[11] LIN Y,ZHANG H. Automatic image annotation via combining low-level colour feature with features learned from convolutional neural networks[J]. Neuro Quantology, 2018,16(6):679-685.

LIN Y,ZHANG H. Automatic image annotation via combining low-level colour feature with features learned from convolutional neural networks[J]. Neuro Quantology, 2018,16(6):679-685.

[12] LIU F,XIANG T,HOSPEDALES T M,et al. Semantic regularization for recurrent image annotation[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu,HI,USA:IEEE, 2017:2872-2880.

Honolulu,HI,USA:IEEE, 2017:2872-2880.

LIU F,XIANG T,HOSPEDALES T M,et al. Semantic regularization for recurrent image annotation[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.

LIU F,XIANG T,HOSPEDALES T M,et al. Semantic regularization for recurrent image annotation[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu,HI,USA:IEEE, 2017:2872-2880.

[13] BREIMAN L. Bagging predictors[J]. Machine Learning, 1996,24(2):123-140.

BREIMAN L. Bagging predictors[J]. Machine Learning, 1996,24(2):123-140.

[14] KRIZHEVSKY A,SUTSKEVER I,HINTON G E. ImageNet classification with deep convolutional neural networks[C]// Advances in Neural Information Processing Systems. Lake Tahoe,Nevada,USA:

[s.n.], 2012:1097-1105.

KRIZHEVSKY A,SUTSKEVER I,HINTON G E. ImageNet classification with deep convolutional neural networks[C]// Advances in Neural Information Processing Systems. Lake Tahoe,Nevada,USA: [s.n.], 2012:1097-1105.

[15] DENG J,DONG W,SOCHER R,et al. ImageNet: a large-scale hierarchical image database[C]//2009 IEEE Conference on Computer Vision and Pattern Recognition. Miami,FL,USA:IEEE, 2009:248- 255.

DENG J,DONG W,SOCHER R,et al. ImageNet: a large-scale hierarchical image database[C]//2009 IEEE Conference on Computer Vision and Pattern Recognition. Miami,FL,USA:IEEE, 2009:248- 255.

严靓, 周欣, 何小海, 熊淑华, 卿粼波. 基于集成分类的暴恐图像自动标注方法[J]. 太赫兹科学与电子信息学报, 2020, 18(2): 306. YAN Liang, ZHOU Xin, HE Xiaohai, XIONG Shuhua, QING Linbo. Violent image annotation using ensemble learning[J]. Journal of terahertz science and electronic information technology, 2020, 18(2): 306.

基于集成分类的暴恐图像自动标注方法

关于本站 Cookie 的使用提示

全站搜索

基于集成分类的暴恐图像自动标注方法

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索