A hybrid holistic/semantic approach for scene classification

Zenghai Chen, Zheru Chi, Hong Fu

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

3 Citations (Scopus)

Abstract

There are two main strategies to tackle scene classification: holistic and semantic. The former characterizes a scene using its global features, while the latter represents a scene by modeling its internal object configuration. Holistic strategy is good at representing scenes with simple contents, but it does not represent well complex scenes that consist of multiple objects. By contrast, semantic strategy is advantageous at recognizing scenes with complex objects, but it does not work well for simple scenes. In this paper, we propose to integrate holistic and semantic strategies to cope with scene classification. In particular, we exploit a deep learning algorithm to learn features for scene representation in the holistic way. For the semantic strategy, we explore a semantic spatial pyramid to represent the spatial object configuration of scenes. The holistic and semantic strategies are integrated using a method proposed by us. Experimental results on a benchmark natural scene dataset demonstrate the effectiveness of our proposed hybrid approach for scene classification, by comparing to several state-of-the-art algorithms.
Original languageEnglish
Title of host publicationProceedings - International Conference on Pattern Recognition
PublisherIEEE
Pages2299-2304
Number of pages6
ISBN (Electronic)9781479952083
DOIs
Publication statusPublished - 1 Jan 2014
Event22nd International Conference on Pattern Recognition, ICPR 2014 - Stockholm, Sweden
Duration: 24 Aug 201428 Aug 2014

Conference

Conference22nd International Conference on Pattern Recognition, ICPR 2014
Country/TerritorySweden
CityStockholm
Period24/08/1428/08/14

Keywords

  • Holistic representation
  • Scene classification
  • Semantic representation
  • Semantic spatial pyramid

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this