Advanced search
Start date
(Reference retrieved automatically from Web of Science through information on FAPESP grant and its corresponding number as mentioned in the publication by the authors.)

Scalable object instance recognition based on keygraph matching

Full text
Dazzi, Estephan [1] ; de Campos, Teofilo [2] ; Hilton, Adrian [3] ; Cesar Jr, Roberto M.
Total Authors: 4
[1] Univ Sao Paulo, Inst Matemat & Estat, Sao Paulo - Brazil
[2] Univ Brasilia, Brasilia, DF - Brazil
[3] Univ Surrey, Ctr Vis Speech & Signal Proc, Guildford, Surrey - England
Total Affiliations: 3
Document type: Journal article
Source: PATTERN RECOGNITION LETTERS; v. 114, n. SI, p. 53-62, OCT 15 2018.
Web of Science Citations: 0

We propose a generalisation of the local feature matching framework, where keypoints are replaced by k-keygraphs, i.e., isomorphic directed attributed graphs of cardinality k whose vertices are keypoints. Keygraphs have structural and topological properties which are discriminative and efficient to compute, based on graph edge length and orientation as well as vertex scale and orientation. Keypoint matching is performed based on descriptor similarity. Next, 2-keygraphs are calculated; as a result, the number of incorrect keypoint matches reduced in 75% (while the correct keypoint matches were preserved). Then, 3-keygraphs are calculated, followed by 4-keygraphs; this yielded a significant reduction of 99% in the number of remaining incorrect keypoint matches. The stage that finds 2-keygraphs has a computational cost equal to a small fraction of the cost of the keypoint matching stage, while the stages that find 3-keygraphs or 4-keygraphs have a negligible cost. In the final stage, RANSAC finds object poses represented as affine transformations mapping images. Our experiments concern large-scale object instance recognition subject to occlusion, background clutter and appearance changes. By using 4-keygraphs, RANSAC needed 1% of the iterations in comparison with 2-keygraphs or simple keypoints. As a result, using 4-keygraphs provided a better efficiency as well as allowed a larger number of initial keypoints matches to be established, which increased performance. (C) 2017 Elsevier B.V. All rights reserved. (AU)

FAPESP's process: 15/22308-2 - Intermediate representations in Computational Science for knowledge discovery
Grantee:Roberto Marcondes Cesar Junior
Support type: Research Projects - Thematic Grants
FAPESP's process: 14/50769-1 - Hand tracking for occupational therapy
Grantee:Roberto Marcondes Cesar Junior
Support type: Regular Research Grants
FAPESP's process: 11/50761-2 - Models and methods of e-Science for life and agricultural sciences
Grantee:Roberto Marcondes Cesar Junior
Support type: Research Projects - Thematic Grants