Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories

This paper presents a method for recognizing scene categories based on approximate global geometric correspondence. This technique works by partitioning the image into increasingly fine sub-regions and computing histograms of local features found inside each sub-region. The resulting "spatial pyramid" is a simple and computationally efficient extension of an orderless bag-of-features image representation, and it shows significantly improved performance on challenging scene categorization tasks. Specifically, our proposed method exceeds the state of the art on the Caltech-101 database and achieves high accuracy on a large database of fifteen natural scene categories. The spatial pyramid framework also offers insights into the success of several recently proposed image descriptions, including Torralba's "gist" and Lowe's SIFT descriptors.

• Type: Conference
• Year: 2006
• Where: CVPR
• Authors: Svetlana Lazebnik, Cordelia Schmid, Jean Ponce
• Keywords: Bag-of-features Image Representation, Challenging Scene Categorization, Computer Vision, CVPR 2006, Global Geometric Correspondence, Natural Scene Categories, Spatial Pyramid Framework