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

2063	Latent Dirichlet allocation - Blei, Ng, et al.
1265	Color indexing - Swain, Ballard - 1991
788	Object class recognition by unsupervised scale-invariant learning - Fergus, Perona, et al. - 2003
561	Modeling the shape of the scene: a holistic representation of the spatial envelope - Oliva, Torralba - 2001
463	A bayesian hierarchical model for learning natural scene categories - Li, Perona - 2005
404	Learning Generative Visual Models from Few Training Examples: An Incremental Bayesian Approach Tested on 101 Object Categories - Fei-Fei, Fergus, et al. - 2004
402	Unsupervised Learning by Probabilistic Latent Semantic Analysis - Hofmann
315	T.: The pyramid match kernel: discriminative classification with sets of image features - Grauman, Darrell - 2005
272	Shape matching and object recognition using low distortion correspondences - Berg, Berg, et al. - 2005
212	Context-based vision system for place and object recognition - Torralba, Murphy, et al. - 2003
200	Recognition without correspondence using multidimensional receptive field histograms - Schiele, Crowley - 2000
198	Indoor-outdoor image classification - Szummer, Picard - 1998
194	Svm-knn: Discriminative nearest neighbor classification for visual category recognition - Zhang, Berg, et al. - 2006
155	Discovering Objects and Their Location in Images - Sivic, Russell, et al. - 2005
131	Weak hypotheses and boosting for generic object detection and recognition - Opelt, Fussenegger, et al. - 2004
112	Recognition with local features: the kernel recipe - Wallraven, Caputo, et al.
104	Content-Based Query of Image Databases, Inspirations from Text Retrieval - Squire, Müller, et al. - 1999
75	Texture orientation for sorting photos "at a glance - Gorkani, Picard - 1994
73	Modeling scenes with local descriptors and latent aspects - Quelhas, Monay, et al. - 2005
59	Categorizing nine visual classes using local appearance descriptors, in: ICPR Workshop Learning for Adaptable Visual Systems - Willamowski, Arregui, et al. - 2004
49	A maximum entropy framework for part-based texture and object recognition - Lazebnik, Schmid, et al. - 2005
42	The structure of locally orderless images - Koenderink, Doorn - 1999
34	Multiresolution histograms and their use for recognition - Hadjidemetriou, Grossberg, et al. - 2004
25	Local Features and Kernels for Classifcation of Texture and Object Categories: An - ZHANG, MARSZALEK, et al.
24	Towards a computational model for object recognition - Lowe