Compact and adaptive spatial pyramids for scene recognition
作者:
Highlights:
•
摘要
Most successful approaches on scene recognition tend to efficiently combine global image features with spatial local appearance and shape cues. On the other hand, less attention has been devoted for studying spatial texture features within scenes. Our method is based on the insight that scenes can be seen as a composition of micro-texture patterns. This paper analyzes the role of texture along with its spatial layout for scene recognition. However, one main drawback of the resulting spatial representation is its huge dimensionality. Hence, we propose a technique that addresses this problem by presenting a compact Spatial Pyramid (SP) representation. The basis of our compact representation, namely, Compact Adaptive Spatial Pyramid (CASP) consists of a two-stages compression strategy. This strategy is based on the Agglomerative Information Bottleneck (AIB) theory for (i) compressing the least informative SP features, and, (ii) automatically learning the most appropriate shape for each category. Our method exceeds the state-of-the-art results on several challenging scene recognition data sets.
论文关键词:Scene recognition,Spatial pyramids,Texture,Dimensionality reduction,Agglomerative information theory
论文评审过程:Received 1 May 2011, Revised 12 April 2012, Accepted 20 April 2012, Available online 4 May 2012.
论文官网地址:https://doi.org/10.1016/j.imavis.2012.04.002