The effect of region segmentation on object categorization

Chih Fong Tsai, Ya Han Hu, Wei Chao Lin

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

1 Scopus citations

Abstract

The success of object categorization is heavily dependent on the extracted image descriptors. In general, image or region segmentation is usually performed to segment an image into several regions or objects, and then some level-level features, such as color and texture, are extracted from each region. As a result, the region descriptor or the combination of multiple region descriptors can be used to represent a specific object or the whole image for categorization. Since there are many well-known region segmentation algorithms proposed in literature, and using different region segmentation algorithms can produce different region descriptors for the same images, no study examines the effect of region segmentation on object categorization. In this paper, we apply three well-known region segmentation algorithms for image feature extraction and representation, which are graph cuts, mean-shift segmentation, and normalized cuts. Then, the support vector machine (SVM) is used as the classifier for object categorization. Our experimental results based on Caltech 5, Caltech 8, and Corel 10 datasets show that the normalized cuts algorithm performs best. In addition, the image feature representation based on multiple region descriptors can provide more discriminative power than using center region descriptors.

Original languageEnglish
Title of host publicationICSPCC 2016 - IEEE International Conference on Signal Processing, Communications and Computing, Conference Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781509027088
DOIs
StatePublished - 22 11 2016
Externally publishedYes
Event2016 IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2016 - Hong Kong, China
Duration: 05 08 201608 08 2016

Publication series

NameICSPCC 2016 - IEEE International Conference on Signal Processing, Communications and Computing, Conference Proceedings

Conference

Conference2016 IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2016
Country/TerritoryChina
CityHong Kong
Period05/08/1608/08/16

Bibliographical note

Publisher Copyright:
© 2016 IEEE.

Keywords

  • image classification
  • image segmentation
  • object categorization

Fingerprint

Dive into the research topics of 'The effect of region segmentation on object categorization'. Together they form a unique fingerprint.

Cite this