Eigencontours: Novel Contour Descriptors Based on Low-Rank Approximation

Novel contour descriptors, called eigencontours, based on low-rank approximation are proposed in this paper. First, we construct a contour matrix containing all object boundaries in a training set. Second, we decompose the contour matrix into eigencontours via the best rank-M approximation. Third, w...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) S. 2657 - 2665
Hauptverfasser: Park, Wonhui, Jin, Dongkwon, Kim, Chang-Su
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.01.2022
Schlagworte:
Approximation algorithms
categorization
Computer vision
grouping and shape analysis; Low-level vision; Recognition: detection
Matrix decomposition
Pattern recognition
retrieval
Segmentation
Training
ISSN:1063-6919
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Novel contour descriptors, called eigencontours, based on low-rank approximation are proposed in this paper. First, we construct a contour matrix containing all object boundaries in a training set. Second, we decompose the contour matrix into eigencontours via the best rank-M approximation. Third, we represent an object boundary by a linear combination of the M eigencontours. We also incorporate the eigencontours into an instance segmentation framework. Experimental results demonstrate that the proposed eigencontours can represent object boundaries more effectively and more efficiently than existing descriptors in a low-dimensional space. Furthermore, the proposed algorithm yields meaningful performances on instance segmentation datasets.
ISSN:1063-6919
DOI:10.1109/CVPR52688.2022.00269