MIF-CNNIF:一种基于CNN的交叉特征的多分类图像数据框架

doi:10.11896/jsjkx.210800267

计算机科学 ›› 2022, Vol. 49 ›› Issue (11A): 210800267-8.doi: 10.11896/jsjkx.210800267

• 图像处理&多媒体技术 • 上一篇下一篇

MIF-CNNIF:一种基于CNN的交叉特征的多分类图像数据框架

王盼红, 朱昌明

上海海事大学信息工程学院上海 201306

出版日期:2022-11-10 发布日期:2022-11-21
通讯作者: 朱昌明(cmzhu@shmtu.edu.cn)
基金资助:
国家自然科学基金(62276164,61602296);上海市"科技创新行动计划"自然科学基金项目(22ZR1427000);晨光计划(18CG54);中国博士后科学基金(2019M651576)

MIF-CNNIF:A Multi-classification Image Data Framework Based on CNN with Intersect Features

WANG Pan-hong, ZHU Chang-ming

College of Information Engineering,Shanghai Maritime University,Shanghai 201306,China

Online:2022-11-10 Published:2022-11-21
About author:WANG Pan-hong,born in 1998,postgraduate.Her main research interests include machine learning,online features selection.
ZHU Chang-ming,born in 1988,Ph.D.candidate at the East China University of Science and Technology.He is an associate professor in Shanghai Maritime University.His research interest covers image processing and multi-view learning.
Supported by:
National Natural Science Foundation of China(62276164,61602296),“Science and Technology Innovation Action Plan” Natural Science Foundation of Shanghai(22ZR1427000),Chenguang Program(18CG54) and China Postdoctoral Science Foundation(2019M651576).

摘要/Abstract

摘要： 近年来,图像多分类任务和深度学习受到越来越多学者的重视,基于卷积神经网络(Convolutional Neural Network,CNN)的多分类图像数据框架也得到了广泛应用。传统的基于卷积神经网络的多分类图像数据学习(MIF-CNN)普遍存在图像处理复杂、特征维数大、时间复杂度高等问题。针对这一问题,提出了一种基于CNN的交叉特征的多分类图像数据框架(MIF-CNNIF)。MIF-CNNIF是一种基于多种特征选择算法得到相交特征并以此交叉特征代替原特征集处理图像多分类任务的框架。在10个多类图像数据集上进行了丰富的对比实验,结果验证了MIF-CNNIF的有效性。MIF-CNNIF的贡献在于:1)使用预先训练好的CNN模型,避免了设置过多参数;2)与MIF-CNN相比,有效降低了特征维度和时间复杂度;3)具有比MIF-CNN更好的平均分类准确率;4)在多分类图像数据集上成功验证了组合特征算法的有效性。

关键词: 卷积神经网络,特征选择,交叉特征,图像多分类,组合特征

Abstract: In recent years,image multi-classification task and deep learning have received increasingly attentions,and multi-classification image data framework based on convolutional neural network(MIF-CNN) has also been widely used.Traditional CNN-based multi-class image data learning generally has a problem that the image processing is complicated,the feature dimensions are large,and the time complexity is high.To solve this problem,this paper proposes a multi-classification image data framework based on CNN with intersect features(MIF-CNNIF).MIF-CNNIF is a framework for performing multi-classification tasks based on intersect features obtained by multiple feature selection algorithms.Through extensive comparative experiments on 10 multi-class image data sets,the results validate the effectiveness of MIF-CNNIF.The contributions of MIF-CNNIF are that,1)it avoids the problem of setting too many parameters with the usage of pre-trained CNN models;2)it keeps features dimension and time cost after comparing with MIF-CNN;3)it has a better average recognition accuracy than MIF-CNN;4)the effectiveness of combined feature algorithms is verified on multi-class image data sets.

Key words: Convolutional neural network, Feature selection, Intersect features, Image multi-class, Combine feature

中图分类号:

TP389

王盼红, 朱昌明. MIF-CNNIF:一种基于CNN的交叉特征的多分类图像数据框架[J]. 计算机科学, 2022, 49(11A): 210800267-8. https://doi.org/10.11896/jsjkx.210800267

WANG Pan-hong, ZHU Chang-ming. MIF-CNNIF:A Multi-classification Image Data Framework Based on CNN with Intersect Features[J]. Computer Science, 2022, 49(11A): 210800267-8. https://doi.org/10.11896/jsjkx.210800267

参考文献

[1]GUO T,DONG J,LI H,et al.Simple convolutional neural network on image classification[C]//2017 IEEE 2nd International Conference on Big Data Analysis(ICBDA).2017.
[2]ZHENG H.Online Feature Selection Based on Passive-Aggressive Algorithm with Retaining Features[C]//Asia-pacific Web Conference.2015:707-719.
[3]CAO M Y.Flower Image Retrieval Based on Cultural Gene Feature Selection [J].Electronic World,2020,591(9):61-62.
[4]SAEYS Y,INZA I,LARRANAGA P.A review of feature selection techniques in bioinformatics[J].Bioinformatics,2007,23(19):2507-2517.
[5]YU L,LIU H.Feature Selection for High-Dimensional Data:A Fast Correlation-Based Filter Solution[C]//Machine Learning,Proceedings of the Twentieth International Conference(ICML 2003).USA,2003.
[6]LIANG Y C.Filter Feature Selection in Confrontation Environment [D].Guangzhou:South China University of Technology,2020.
[7]DASH M,GOPALKRISHNAN V.Distance Based Feature Se-lection for Clustering Microarray Data[C]//International Conference on Database Systems for Advanced Applications.2008.
[8]CHENG Y W,LI G F,JIANG G Z,et al.A bidirectional recursive EMG feature selection method based on EMG signal.CN111209857A[P].2020.
[9]CHEN C J,JIANG L,LEI N,et al.Interactive feature selection method based on crowdsourcing learning[J].Science in China:Information Science,2020,50(6):20-38.
[10]XU Z,RONG J,YE J,et al.Non-Monotonic Feature Selection[C]//Proceedings of the 26th Annual International Conference on Machine Learning.Canada,2009.
[11]NICOLETTA D,PES B.A Framework for Multi-class Learning in Micro-array Data Analysis[C]//Conference on Artificial Intelligence in Medicine in Europe.Berlin:Springer, 2009.
[12]ALSALANI M G,ELREFAEI L A.Convolutional Neural Network Based Feature Extraction for IRIS Recognition[J].International Journal of Computer Science & Information Technology,2018,10(2):65-78.
[13]ZENG ST,CAO Y C,LIN Q,et al.Classification of SPECT pulmonary perfusion images based on ResNet depth model [J].Journal of Northwest Minzu University(Cience Dition),2021,42(2):27-35.
[14]KADHIM M A,ABED M H.Convolutional Neural Network for Satellite Image Classification[J/OL].Intelligent Information and Database Systems:Recent Developments,2019.https://www.researchgate.net/publication/331557018_Convolutional_Neural_Network_for_Satellite_Image_Classification.
[15]DEWI C,CHEN R.Human Activity Recognition Based on Evolution of Features Selectionand Random Forest[C]//2019 IEEE International Conference on Systems.Man and Cybernetics(SMC).2019.
[16]RAO H,SHI X,RODRIGUE A K,et al.Feature selection based on artificial bee colony and gradient boosting decision tree[J/OL].Applied Soft Computing,2019,74:634-642.https://www.sciencedirect.com/science/article/abs/pii/S1568494618305933.
[17]DING P,XU A J,ZHOU S Y.Tea yield prediction based on gradient lifting decision tree and multi-feature combination [J].Southwest Agricultural Journal,2021,34(7):1556-1563.
[18]GAO Y.Simulation of carbon dioxide flux based on adaptiveneurofuzzy inference system [D].Beijing:Beijing Forestry University,2019.
[19]CHEN J,WANG J,WANG X,et al.Predicting Drug Target Interactions Based on GBDT[C]//International Conference on Machine Learning and Data Mining in Pattern Recognition.Cham,2018:202-212.
[20]CHEN J,ZHANG Y X,JIANG Y Y.Texture image classification method based on multi-feature and random forest [J].Sensors and Microsystems,2019,38,334(12):64-67.
[21]GRARLI I,ADEL M,BOURENNAME S,et al.Histogram-Based Features Selection and Volume of Interest Ranking for Brain PET Image Classification[C]//IEEE Journal of Translational Engineering in Health and Medicine.2018.
[22]GUYON I M,ANDR E.An introduction to variable and feature selection[J/OL].The Journal of Machine Learning Research,2003,3(Mar):1157-1182.https://www.jmlr.org/papers/volume3/guyon03a/guyon03a.pdf?ref=driverlayer.com/web.
[23]DIAS P A,TABB A,MEDEIROS H.Apple flower detectionusing deep convolutional networks[J/OL].Computers in Industry,2018,99:17-28.https://www.sciencedirect.com/science/article/abs/pii/S016636151730502X.
[24]GHAZI M M,YANIKOGLU B,APTOULA E.Plant identification using deep neural networks via optimization of transfer learning parameters[J].Neurocomputing,2017,235(26):228-235.
[25]SARDOGAM M,TUNCER A,OZEN Y.Plant Leaf Disease Detection and Classification Based on CNN with LVQ Algorithm[C]//2018 3rd International Conference on Computer Science and Engineering(UBMK).2018.
[26]PAWARA P,OKAFOR E,SCHOMAKER L,et al.A.Wiering.Data Augmentation for Plant Classification[C]//Advanced Concepts for Intelligent Vision Systems(ACIVS2017).2017.
[27]NAGASUBRAMANIAN K,JONES S,SINGH A K,et al.Explaining hyperspectral imaging based plant disease identification: 3D CNN and saliency maps[J].arXiv:1804.08831,2018.
[28]GAYATHRI S,GOPI V P,PALANISAMY P A.lightweight CNN for Diabetic Retinopathy classification from fundus images[J/OL].Biomedical Signal Processing and Control.2020,62.https://www.sciencedirect.com/science/article/abs/pii/S1746809420302676.
[29]VAPNIK V.Statistical Learning TheoryLos[M/OL].DBLP,1998.https://www.researchgate.net/publication/220694713_Statistical_Learning_Theory.
[30]DEMIAR J,SCHUURMANS D.Statistical Comparisons ofClassifiers over Multiple DataSets[J].Journal of Machine Learning Research.2006,7(1):1-30.
[31]ZHU C,GAO D.Improved multi-kernel classification machine withNyström approximation technique[J].Pattern Recognition.2015,48(4):1490-1590.
[32]ZHU C,WANG P,MA L,et al.Global and local multi-view multi-label learning with incomplete views and labels[J].Neural Computing and Applications,2020,371(2):67-77.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

MIF-CNNIF:一种基于CNN的交叉特征的多分类图像数据框架

MIF-CNNIF:A Multi-classification Image Data Framework Based on CNN with Intersect Features

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 9

Metrics

本文评价

推荐阅读 0

[1]	冉煜, 张莉. R-YOLOv5:自动切割的旋转的文本检测模型 R-YOLOv5:Auto-cutting,Rotated Text Detection Model 计算机科学, 2022, 49(11A): 210900185-6. https://doi.org/10.11896/jsjkx.210900185
[2]	马宾, 付永康, 王春鹏, 李健, 王玉立. 基于GDIoU损失函数的YOLOv4绝缘子高效定位算法 High Performance Insulators Location Scheme Based on YOLOv4 with GDIoU Loss Function 计算机科学, 2022, 49(6A): 412-417. https://doi.org/10.11896/jsjkx.210600089
[3]	刘奇, 陈红梅, 罗川. 基于改进的蝗虫优化算法的红细胞供应预测方法 Method for Prediction of Red Blood Cells Supply Based on Improved Grasshopper Optimization Algorithm 计算机科学, 2021, 48(2): 224-230. https://doi.org/10.11896/jsjkx.200600016
[4]	霍丹, 张生杰, 万路军. 基于上下文的情感词向量混合模型 Context-based Emotional Word Vector Hybrid Model 计算机科学, 2020, 47(11A): 28-34. https://doi.org/10.11896/jsjkx.191100114
[5]	庄志刚, 许青林. 一种结合多尺度特征图和环型关系推理的场景图生成模型 Scene Graph Generation Model Combining Multi-scale Feature Map and Ring-type RelationshipReasoning 计算机科学, 2020, 47(4): 136-141. https://doi.org/10.11896/jsjkx.190300002
[6]	刘玉红,刘树英,付福祥. 基于卷积神经网络的压缩感知重构算法优化 Optimization of Compressed Sensing Reconstruction Algorithms Based on Convolutional Neural Network 计算机科学, 2020, 47(3): 143-148. https://doi.org/10.11896/jsjkx.190100199
[7]	郭佳. 基于改进的人工神经网络对存储系统性能进行预测的方法 Method of Predicting Performance of Storage System Based on Improved Artificial Neural Network 计算机科学, 2019, 46(6A): 52-55.
[8]	崔璐,张鹏,车进. 基于深度神经网络的遥感图像分类算法综述 Overview of Deep Neural Network Based Classification Algorithms for Remote Sensing Images 计算机科学, 2018, 45(6A): 50-53.
[9]	任天赐, 黄向生, 丁伟利, 安重阳, 翟鹏博. 全局双边网络的语义分割算法 Global Bilateral Segmentation Network for Segmantic Segmentation 计算机科学, 2020, 47(6A): 161-165. https://doi.org/10.11896/JsJkx.191200127