Scene categorization based on heterogeneous features

Fuxiang Lu; Xiaokang Yang; Rui Zhang; Songyu Yu

doi:10.1117/12.863481

Translator Disclaimer

4 August 2010 Scene categorization based on heterogeneous features

Fuxiang Lu, Xiaokang Yang, Rui Zhang, Songyu Yu

Author Affiliations +

Proceedings Volume 7744, Visual Communications and Image Processing 2010; 77441U (2010) https://doi.org/10.1117/12.863481
Event: Visual Communications and Image Processing 2010, 2010, Huangshan, China

Abstract

In this paper we present a complete framework for scene categorization that builds upon and extends several recent ideas including spatial pyramid representation and a variety of base local descriptors which have different discriminative power and invariance from task to task. Furthermore, we propose two strategies: sum-max and max-max, used to effectively combine diverse source of data in a unified setting way. Our approach shows significantly improved performance on a large, challenging data set of fifteen natural scene categories. Owing to combination of complementary information cues, our approach is expected to equally applicable to a range of tasks.

Citation Download Citation

Fuxiang Lu, Xiaokang Yang, Rui Zhang, and Songyu Yu "Scene categorization based on heterogeneous features", Proc. SPIE 7744, Visual Communications and Image Processing 2010, 77441U (4 August 2010); https://doi.org/10.1117/12.863481

ACCESS THE FULL ARTICLE