Abstract

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. 1.

Citations

2349	Latent Dirichlet Allocation - Blei, Ng, et al. - 2003
1320	Color indexing - Swain, Ballard - 1991
868	Object class recognition by unsupervised scale-invariant learning - Fergus, Perona, et al. - 2003
665	Modeling the shape of the scene: a holistic representation of the spatial envelope - Oliva, Torralba - 2001
539	A Bayesian Hierarchical Model for Learning Natural Scene Categories - Fei-Fei, Perona - 2005
460	Learning generative visual models from few training examples: an incremental Bayesian approach tested on 101 object cateories - Fei-Fei, Fergus, et al. - 2004
446	Unsupervised Learning by Probabilistic Latent Semantic Analysis - Hofmann - 2001
367	Pyramid match kernels: Discriminative classification with sets of image features - Darrell - 2005
293	Shape matching and object recognition using low distortion correspondence - Berg, Berg, et al. - 2005
233	Context-based vision system for place and object recognition - Torralba, Murphy, et al. - 2003
210	SVM-KNN: Discriminative nearest neighbor classification for visual category recognition - Zhang, Berg, et al. - 2006
207	Object recognition without correspondence using multidimensional receptive field histograms - Schiele, Crowley
206	Indoor-outdoor image classification - Szummer, Picard - 1998
175	Discovering objects and their location in images - Sivic, Russell, et al.
137	weak hypotheses and boosting for generic object detection and recognition - Opelt, Fussenegger, et al. - 2004
132	Recognition with local features: the kernel recipe - Wallraven, Caputo, et al. - 2003
108	Content-based query of image databases: inspirations from text retrieval”, Pattern Recognition Letters - Squire, Müller, et al. - 2000
81	Modeling scenes with local descriptors and latent aspects - Quelhas, Monay, et al. - 2005
78	Texture Orientation for Sorting Photos at a Glance - Gorkani, Picard - 1994
64	Categorizing nine visual classes using local appearance descriptors - Willamowski, Arregui, et al. - 2004
54	A maximum entropy framework for part-based texture and object recognition - Lazebnik, Schmid, et al. - 2005
46	The structure of locally orderless images - Koenderink, Doorn - 1999
39	Multiresolution histograms and their use for recognition - Hadjidemetriou, Grossberg, et al.
26	Local features and kernels for classifcation of texture and object categories: A comprehensive study. Int - Zhang, Marszalek, et al.
25	Towards a computational model for object recognition - Lowe - 2000