Files and links (1)
https://scholarship.libraries.rutgers.edu/esploro/outputs/technicalDocumentation/View-Based-Object-Recognition-Using-Saliency-Maps/991031549982604646
SubmittedOpen Access (License Unspecified), Open
Journal article
View-based object recognition using saliency maps
Image and vision computing, v 17(5), pp 445-460
1999
Featured in Collection : UN Sustainable Development Goals @ Drexel
Abstract
We introduce a novel view-based object representation, called the saliency map graph (SMG), which captures the salient regions of an object view at multiple scales using a wavelet transform. This compact representation is highly invariant to translation, rotation (image and depth), and scaling, and offers the locality of representation required for occluded object recognition. To compare two saliency map graphs, we introduce two graph similarity algorithms. The first computes the topological similarity between two SMGs, providing a coarse-level matching of two graphs. The second computes the geometrical similarity between two SMGs, providing a fine-level matching of two graphs. We test and compare these two algorithms on a large database of model object views.
Metrics
Details
- Title
- View-based object recognition using saliency maps
- Creators
- Ali Shokoufandeh - Rutgers, The State University of New JerseyIvan Marsic - School of Engineering, Electrical & Computer EngineeringSven J. Dickinson - Rutgers, The State University of New Jersey
- Publication Details
- Image and vision computing, v 17(5), pp 445-460
- Publisher
- Elsevier
- Resource Type
- Journal article
- Language
- English
- Academic Unit
- Computer Science
- Web of Science ID
- WOS:000079370600012
- Scopus ID
- 2-s2.0-0033115072
- Other Identifier
- 991019203328104721
UN Sustainable Development Goals (SDGs)
This publication has contributed to the advancement of the following goals:
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Web of Science research areas
- Computer Science, Artificial Intelligence
- Computer Science, Software Engineering
- Computer Science, Theory & Methods
- Engineering, Electrical & Electronic
- Optics