Compact and adaptive spatial pyramids for scene recognition

• Published in: Image and vision computing Vol. 30; no. 8; pp. 492 - 500
• Main Authors: M. Elfiky, Noha, Gonzàlez, Jordi, Roca, F. Xavier
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.08.2012
• Subjects: Agglomerative information theory; Compressing; Dimensionality reduction; Pyramids; Recognition; Representations; Scene recognition; Spatial pyramids; Strategy; Surface layer; Texture; Dimensionality reduction; Agglomerative information theory; Scene recognition; Texture; Spatial pyramids
• ISSN: 0262-8856; 1872-8138
• DOI: 10.1016/j.imavis.2012.04.002

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. ► A major drawback of Spatial Pyramid (SP) is the high dimensionality. We present a novel framework to obtain compact SP. ► We present compression strategies based on an extension to the agglomerative information bottleneck algorithm. ► We present a novel spatial texture descriptor (PC-TPLBP) for the problem of scene recognition. ► We show the importance of combining PC-TPLBP (regional) with pixel-based features (local) for improving performance.