Texture Superpixel Clustering from Patch-based Nearest Neighbor Matching

Abstract : 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.
Complete list of metadatas

Cited literature [26 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02059490
Contributor : Rémi Giraud <>
Submitted on : Tuesday, June 4, 2019 - 8:09:38 PM
Last modification on : Friday, June 14, 2019 - 11:14:25 AM

File

PM_SP.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02059490, version 1

Citation

Rémi Giraud, Yannick Berthoumieu. Texture Superpixel Clustering from Patch-based Nearest Neighbor Matching. European Signal Processing Conference (EUSIPCO 2019), Sep 2019, La Corogne, Spain. ⟨hal-02059490⟩

Share

Metrics

Record views

88

Files downloads

217