欢迎来到天天文库
浏览记录
ID:55785066
大小:983.76 KB
页数:10页
时间:2020-06-01
《融合显著信息的层次特征学习图像分类.pdf》由会员上传分享,免费在线阅读,更多相关内容在行业资料-天天文库。
1、计算机研究与发展DOI:10.7544/issnl000—1239.2014.20140138JournalofComputerResearchandDevelopment51(9):1919—1928,2014融合显著信息的层次特征学习图像分类祝军赵杰煜董振宇(宁波大学信息科学与工程学院浙江宁波315211)(jun.zhu.CS@gma1.corn)ImageClassificationUsingHierarchicalFeatureLearningMethodCombinedwithImageSaliencyZhuJun,ZhaoJieyu,andDo
2、ngZhenyu(CollegeofInformationScienceandEngineering,NingboUniversity,Ningbo,Zhejiang315211)AbstractEfficientfeaturerepresentationsforimagesareessentialinmanycomputervisiontasks.Inthispaper,ahierarchicalfeaturerepresentationcombinedwithimagesaliencyisproposedbasedonthetheoryofvisuals
3、aliencyanddeeplearning,whichbuildsafeaturehierarchylayer-by—layer.Eachfeaturelearninglayeriscomposedofthreeparts:sparsecoding,saliencymaxpoolingandcontrastnormalization.Tospeedupthesparsecodingprocess,weproposebatchorthogonalmatchingpursuitwhichdiffersfromthetraditiona1method.Thesa
4、lientinformationisintroducedintotheimagesparserepresentation,whichcompressesthefeaturerepresentationandstrengthensthesemanticinformationofthefeaturerepresentation.Simultaneously,contrastnormalizationeffectivelyreducestheimpactoflocalvariationsinilluminationandforeground—backgroundc
5、ontrast,andenhancestherobustnessofthefeaturerepresentation.Insteadofusinghand—crafteddescriptors,ourmodellearnsaneffectiveimagerepresentationdirectlyfromimagesinanunsuperviseddata~drivenmanner.ThefinalimageclassificationisimplementedwithalinearSVMclassifierusingthelearnedimagerepre
6、sentation.Wecompareourmethodwithmanystate—of——the—artalgorithmsincludingconvolutionaldeepbeliefnetworks,SIFTbasedsinglelayerormulti—layersparsecodingmethods,andsomekernelbasedfeaturelearningapproaches.TheexperimentalresultsontwocommonlyusedbenchmarkdatasetsCaltech101andCaltech256sh
7、owthatourmethodconsistentlyandsignificantlyimprovestheperformance.Keywordsfeaturelearning;hierarchicalsparsecoding;imagesaliency;imageclassification;saliencymaxpooling摘要高效的图像特征表示是计算机视觉的基础.基于图像的视觉显著性机制及深度学习模型的思想,提出一种融合图像显著性的层次稀疏特征表示用于图像分类.这种层次特征学习每一层都由3个部分组成:稀疏编码、显著性最大值;F聚(saliencym
8、axpooling)和对比度归一化.通过在图像层次稀
此文档下载收益归作者所有