Multi-class object recognition and segmentation based on multi-feature fusion modeling

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

The paper presents a new theme and region based CRF model to realize the combination of multiple image texture, shape, context and location features. The model parameters are learned by Joint-boosting algorithm. The over-segmentation algorithm is used to divide the image into finite continuous regions. The constraint relationship between image theme, region and pixel is considered while modeling feature potentials and optimizing parameter's selection to improve the accuracy of multi-class object recognition and segmentation. The experimental results on MRSC-21 database show that the accuracy of the algorithms proposed in this paper outperforms that of the other existing algorithms. Especially by concerning regions and theme factors, our model obtains improved accuracy of segmentation and recognition of highly structured classes of objects with large shape variance and fewer training examples.

Original languageEnglish
Title of host publicationProceedings - 2015 IEEE 12th International Conference on Ubiquitous Intelligence and Computing, 2015 IEEE 12th International Conference on Advanced and Trusted Computing, 2015 IEEE 15th International Conference on Scalable Computing and Communications, 2015 IEEE International Conference on Cloud and Big Data Computing, 2015 IEEE International Conference on Internet of People and Associated Symposia/Workshops, UIC-ATC-ScalCom-CBDCom-IoP 2015
EditorsJianhua Ma, Ali Li, Huansheng Ning, Laurence T. Yang
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages336-339
Number of pages4
ISBN (Electronic)9781467372114
DOIs
StatePublished - 20 Jul 2016
EventProceedings - 2015 IEEE 12th International Conference on Ubiquitous Intelligence and Computing, 2015 IEEE 12th International Conference on Advanced and Trusted Computing, 2015 IEEE 15th International Conference on Scalable Computing and Communications, 2015 IEEE International Conference on Cloud and Big Data Computing, 2015 IEEE International Conference on Internet of People and Associated Symposia/Workshops, UIC-ATC-ScalCom-CBDCom-IoP 2015 - Beijing, China
Duration: 10 Aug 201514 Aug 2015

Publication series

NameProceedings - 2015 IEEE 12th International Conference on Ubiquitous Intelligence and Computing, 2015 IEEE 12th International Conference on Advanced and Trusted Computing, 2015 IEEE 15th International Conference on Scalable Computing and Communications, 2015 IEEE International Conference on Cloud and Big Data Computing, 2015 IEEE International Conference on Internet of People and Associated Symposia/Workshops, UIC-ATC-ScalCom-CBDCom-IoP 2015

Conference

ConferenceProceedings - 2015 IEEE 12th International Conference on Ubiquitous Intelligence and Computing, 2015 IEEE 12th International Conference on Advanced and Trusted Computing, 2015 IEEE 15th International Conference on Scalable Computing and Communications, 2015 IEEE International Conference on Cloud and Big Data Computing, 2015 IEEE International Conference on Internet of People and Associated Symposia/Workshops, UIC-ATC-ScalCom-CBDCom-IoP 2015
Country/TerritoryChina
CityBeijing
Period10/08/1514/08/15

Keywords

  • CRF model
  • Image segmentation
  • Joint boost
  • Multi feature fusion
  • Multi-class object recognition

Fingerprint

Dive into the research topics of 'Multi-class object recognition and segmentation based on multi-feature fusion modeling'. Together they form a unique fingerprint.

Cite this