Building holistic descriptors for scene recognition

Liu, Li, Shao, Ling and Li, Xuelong (2013) Building holistic descriptors for scene recognition. In: ACM Multimedia 2013 - 21st ACM International Conference on Multimedia, 21st - 25th October 2013, Barcelona, Spain.

Full text not available from this repository. (Request a copy)
Official URL: http://dx.doi.org/10.1145/2502081.2502095

Abstract

Real-world scene recognition has been one of the most challenging research topics in computer vision, due to the tremendous intraclass variability and the wide range of scene categories. In this paper, we successfully apply an evolutionary methodology to automatically synthesize domain-adaptive holistic descriptors for the task of scene recognition, instead of using hand-tuned descriptors. We address this as an optimization problem by using multi-objective genetic programming (MOGP). Specifically, a set of primitive operators and filters are first randomly assembled in the MOGP framework as tree-based combinations, which are then evaluated by two objective fitness criteria i.e., the classification error and the tree complexity. Finally, the best-so-far solution selected by MOGP is regarded as the (near-)optimal feature descriptor for scene recognition. We have evaluated our approach on three realistic scene datasets: MIT urban and nature, SUN and UIUC Sport. Experimental results consistently show that our MOGP-generated descriptors achieve significantly higher recognition accuracies compared with state-of-the-art hand-crafted and machine-learned features.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Computing methodologies, Artificial intelligence, Computer vision problems, Object recognition
Subjects: G400 Computer Science
Department: Faculties > Engineering and Environment > Computer and Information Sciences
Depositing User: Paul Burns
Date Deposited: 16 Jun 2015 11:20
Last Modified: 13 Oct 2019 00:36
URI: http://nrl.northumbria.ac.uk/id/eprint/22940

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics