Empirical curvelet based Fully Convolutional Network for supervised texture image segmentation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Huang, Yuan, Zhou, Fugen, Gilles, Jerome
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916457334439936
author Huang, Yuan
Zhou, Fugen
Gilles, Jerome
author_facet Huang, Yuan
Zhou, Fugen
Gilles, Jerome
contents In this paper, we propose a new approach to perform supervised texture classification/segmentation. The proposed idea is to feed a Fully Convolutional Network with specific texture descriptors. These texture features are extracted from images by using an empirical curvelet transform. We propose a method to build a unique empirical curvelet filter bank adapted to a given dictionary of textures. We then show that the output of these filters can be used to build efficient texture descriptors utilized to finally feed deep learning networks. Our approach is finally evaluated on several datasets and compare the results to various state-of-the-art algorithms and show that the proposed method dramatically outperform all existing ones.
format Preprint
id arxiv_https___arxiv_org_abs_2410_21562
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Empirical curvelet based Fully Convolutional Network for supervised texture image segmentation
Huang, Yuan
Zhou, Fugen
Gilles, Jerome
Computer Vision and Pattern Recognition
In this paper, we propose a new approach to perform supervised texture classification/segmentation. The proposed idea is to feed a Fully Convolutional Network with specific texture descriptors. These texture features are extracted from images by using an empirical curvelet transform. We propose a method to build a unique empirical curvelet filter bank adapted to a given dictionary of textures. We then show that the output of these filters can be used to build efficient texture descriptors utilized to finally feed deep learning networks. Our approach is finally evaluated on several datasets and compare the results to various state-of-the-art algorithms and show that the proposed method dramatically outperform all existing ones.
title Empirical curvelet based Fully Convolutional Network for supervised texture image segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.21562