Texture Superpixel Clustering from Patch-based Nearest Neighbor Matching

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Giraud, Rémi, Berthoumieu, Yannick
Format: Preprint
Veröffentlicht: 2020
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909802931683328
author Giraud, Rémi
Berthoumieu, Yannick
author_facet Giraud, Rémi
Berthoumieu, Yannick
contents Superpixels are widely used in computer vision applications. Nevertheless, decomposition methods may still fail to efficiently cluster image pixels according to their local texture. In this paper, we propose a new Nearest Neighbor-based Superpixel Clustering (NNSC) method to generate texture-aware superpixels in a limited computational time compared to previous approaches. We introduce a new clustering framework using patch-based nearest neighbor matching, while most existing methods are based on a pixel-wise K-means clustering. Therefore, we directly group pixels in the patch space enabling to capture texture information. We demonstrate the efficiency of our method with favorable comparison in terms of segmentation performances on both standard color and texture datasets. We also show the computational efficiency of NNSC compared to recent texture-aware superpixel methods.
format Preprint
id arxiv_https___arxiv_org_abs_2003_04414
institution arXiv
publishDate 2020
record_format arxiv
spellingShingle Texture Superpixel Clustering from Patch-based Nearest Neighbor Matching
Giraud, Rémi
Berthoumieu, Yannick
Computer Vision and Pattern Recognition
Superpixels are widely used in computer vision applications. Nevertheless, decomposition methods may still fail to efficiently cluster image pixels according to their local texture. In this paper, we propose a new Nearest Neighbor-based Superpixel Clustering (NNSC) method to generate texture-aware superpixels in a limited computational time compared to previous approaches. We introduce a new clustering framework using patch-based nearest neighbor matching, while most existing methods are based on a pixel-wise K-means clustering. Therefore, we directly group pixels in the patch space enabling to capture texture information. We demonstrate the efficiency of our method with favorable comparison in terms of segmentation performances on both standard color and texture datasets. We also show the computational efficiency of NNSC compared to recent texture-aware superpixel methods.
title Texture Superpixel Clustering from Patch-based Nearest Neighbor Matching
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2003.04414