NDLI: Combining attention and recognition for rapid scene analysis

Content Provider	IEEE Xplore Digital Library
Author	Bonaiuto, J.J. Itti, L.
Copyright Year	2005
Description	Author affiliation: University of Southern California , Los Angeles (Bonaiuto, J.J.)
Abstract	Bottom-up visual attention allows primates to quickly select regions of an image that contain salient objects. In artificial systems, restricting the task of object recognition to these regions allows faster recognition and unsupervised learning of multiple objects in cluttered scenes. A problem is that objects superficially dissimilar to the target are given the same consideration in recognition as similar objects. Here we investigate rapid pruning of the recognition search space using the already-computed low-level features that guide attention. Itti and Kochs bottom-up visual attention algorithm selects salient locations based on low-level features such as contrast, orientation, color, and intensity. Lowes SIFT recognition algorithm then extracts a signature of the attended object, for comparison with the object database. The database search is prioritized for objects which better match the low-level features used to guide attention to the current candidate for recognition. The SIFT signatures of prioritized database objects are then checked for match against the attended candidate. By comparing performance of Lowes recognition algorithm and Itti and Kochs bottom-up attention model with or without search space pruning, we demonstrate that our pruning approach improves the speed of object recognition in complex natural scenes.
Starting Page	90
Ending Page	90
File Size	322575
Page Count	1
File Format	PDF
ISBN	0769523722
ISSN	10636919
DOI	10.1109/CVPR.2005.432
Language	English
Publisher	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher Date	2005-09-21
Publisher Place	USA
Access Restriction	Subscribed
Rights Holder	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subject Keyword	Image analysis Neuroscience Object oriented databases Target recognition Layout Object detection Spatial databases Object recognition Visual databases Unsupervised learning
Content Type	Text
Resource Type	Article
Subject	Computer Vision and Pattern Recognition Software

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

Is bottom-up attention useful for object recognition?

Joint visual vocabulary for animal classification

Object-graphs for context-aware category discovery

Learning hierarchical models of scenes, objects, and parts

Object recognition using the Connection Machine

Object recognition using invariant profiles

Topic models for scene analysis and abnormality detection

Probabilistic spatial context models for scene content understanding

Epitomic location recognition

Combining attention and recognition for rapid scene analysis

Similar Documents

Is bottom-up attention useful for object recognition?

Joint visual vocabulary for animal classification

Object-graphs for context-aware category discovery

Learning hierarchical models of scenes, objects, and parts

Object recognition using the Connection Machine

Object recognition using invariant profiles

Topic models for scene analysis and abnormality detection

Probabilistic spatial context models for scene content understanding

Epitomic location recognition

Combining attention and recognition for rapid scene analysis