资源分类
》 资源 》论文》OTC: A Novel Local Descriptor for Scene Classification

OTC: A Novel Local Descriptor for Scene Classification

2020-04-06 | |  61 |   44 |   0

Abstract

Scene classification is the task of determining the scene type in which a photograph was taken. In this paper we present a novel lo- cal descriptor suited for such a task: Oriented Texture Curves (OTC). Our descriptor captures the texture of a patch along multiple orienta- tions, while maintaining robustness to illumination changes, geometric distortions and local contrast differences. We show that our descriptor outperforms all state-of-the-art descriptors for scene classification algo- rithms on the most extensive scene classification benchmark to-date.

上一篇：Active Deformable Part Models Inference*

下一篇：Pipelining Localized Semantic Features for Fine-Grained Action Recognition

用户评价
全部评价

热门资源

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • The Variational S...

    Unlike traditional images which do not offer in...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Rating-Boosted La...

    The performance of a recommendation system reli...