Multimodal learning for view-based 3D object classification.pdfVIP

下载本文档

10
0
约3.45万字
约 7页
2017-03-16 发布于天津
举报
版权申诉

Multimodal learning for view-based 3D object classification.pdf

1、本文档共7页，可阅读全部内容。
2、原创力文档（book118）网站文档一经付费（服务费），不意味着购买了该文档的版权，仅供个人/单位学习、研究之用，不得用于商业用途，未经授权，严禁复制、发行、汇编、翻译或者网络传播等，侵权必究。
3、本站所有内容均由合作方或网友上传，本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺！文档内容仅供研究参考，付费前请自行鉴别。如您付费，意味着您自己接受本站规则且自行承担风险，本站不退款、不进行额外附加服务；查看《如何避免下载的几个坑》。如果您已付费下载过本站文档，您可以点击这里二次下载。
4、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等，请点击“版权申诉”（推荐），也可以打举报电话：400-050-0827(电话支持时间：9:00-18:30)。
5、该文档为VIP文档，如果想要下载，成为VIP会员后，下载免费。
6、成为VIP后，下载本文档将扣除1次下载权益。下载后，不支持退款、换文档。如有疑问请联系我们。
7、成为VIP后，您将拥有八大权益，权益包括：VIP文档下载权益、阅读免打扰、文档格式转换、高级专利检索、专属身份标志、高级客服、多端互通、版权登记。
8、VIP文档为合作方或网友上传，每下载1次，网站将根据用户上传文档的质量评分、类型等，对文档贡献者给予高额补贴、流量扶持。如果你也想贡献VIP文档。上传文档

Multimodal learning for view-based 3D object classification.pdf

Neurocomputing 195 (2016) 23–29 Contents lists available at ScienceDirect Neurocomputing journal homepage: /locate/neucom Multimodal learning for view-based 3D object classi?cation Fuhai Chen a,b, Rongrong Ji a,b, Liujuan Cao a,b,n a Fujian Key Laboratory of Sensing and Computing for Smart City, China b School of Information Science and Engineering, Xiamen University, Xiamen, Fujian 361005, China article info Article history: Received 7 April 2015 Received in revised form 25 August 2015 Accepted 19 September 2015 Available online 27 February 2016 Keywords: View-based 3D object Multi-task feature selection Multimodal SVM abstract Nowadays by employing many machine learning and pattern classi?cation methods in object classi?cation, the view-based 3D object classi?cation, an emerging research topic, becomes a major research focus. However, most existing researches focus on only a single modality of image features for the object classi?cation, although recent studies have shown that different kinds of features may provide complementary information for 3D object classi?cation. In this paper, we propose the multimodal support vector machine to combine three modalities of image features, i.e., Sift descriptor, Outline Fourier transform descriptor, and Zernike Moments descriptor to discriminate the multiple classes of object, where each kernel corresponds to each modality. In this way, not only the independence of each modality but also the interrelation between them are both taken into considered. And we further employ multi-task feature selection via the l2-norm regularization after feature extraction to improve the performance of ?nal classi?cation. The experiments conducted in ETH-80 image set demonstrate the effectiveness and superiority of our method. 2016 Elsevier B.V. All rights reserved. 1. Introduction Nowadays with the rapid development of websites and the widespread popularity of mobile devices, view-based 3D object classi?cation and retrieval have been drawing