Discriminant Saliency, the Detection of Suspicious Coincidences, and Applications to Visual Recognition
- 2 February 2009
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Ieee Transactions On Pattern Analysis and Machine Intelligence
- Vol. 31 (6), 989-1005
- https://doi.org/10.1109/tpami.2009.27
Abstract
A discriminant formulation of top-down visual saliency, intrinsically connected to the recognition problem, is proposed. The new formulation is shown to be closely related to a number of classical principles for the organization of perceptual systems, including infomax, inference by detection of suspicious coincidences, classification with minimal uncertainty, and classification with minimum probability of error. The implementation of these principles with computational parsimony, by exploitation of the statistics of natural images, is investigated. It is shown that Barlow's principle of inference by the detection of suspicious coincidences enables computationally efficient saliency measures which are nearly optimal for classification. This principle is adopted for the solution of the two fundamental problems in discriminant saliency, feature selection and saliency detection. The resulting saliency detector is shown to have a number of interesting properties, and act effectively as a focus of attention mechanism for the selection of interest points according to their relevance for visual recognition. Experimental evidence shows that the selected points have good performance with respect to 1) the ability to localize objects embedded in significant amounts of clutter, 2) the ability to capture information relevant for image classification, and 3) the richness of the set of visual attributes that can be considered salient.Keywords
This publication has 52 references indexed in Scilit:
- A Thousand Words in a SceneIeee Transactions On Pattern Analysis and Machine Intelligence, 2007
- An Exemplar Model for Learning Object ClassesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- Local Features and Kernels for Classification of Texture and Object Categories: A Comprehensive StudyInternational Journal of Computer Vision, 2006
- Generic object recognition with boostingIeee Transactions On Pattern Analysis and Machine Intelligence, 2006
- Learning object categories from Google's image searchPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Selection of scale-invariant parts for object class recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Wavelet-based texture retrieval using generalized Gaussian density and Kullback-Leibler distanceIEEE Transactions on Image Processing, 2002
- Estimation of shape parameter for generalized Gaussian distributions in subband decompositions of videoIEEE Transactions on Circuits and Systems for Video Technology, 1995
- A theory for multiresolution signal decomposition: the wavelet representationIeee Transactions On Pattern Analysis and Machine Intelligence, 1989
- A Combined Corner and Edge DetectorPublished by British Machine Vision Association and Society for Pattern Recognition ,1988