Inverse texture synthesis in wavelet packet trees
Inverse texture synthesis (ITS) plays an important role in many computer vision applications. It aims at generating small compaction images to capture significant features of textures, from which arbitrarily large images with similar textures can be re‐synthesised. This study presents a fast approac...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2015-04-01
|
Series: | IET Computer Vision |
Subjects: | |
Online Access: | https://doi.org/10.1049/iet-cvi.2013.0262 |
_version_ | 1797684813840252928 |
---|---|
author | Hsi‐Chin Hsin Tze‐Yun Sung |
author_facet | Hsi‐Chin Hsin Tze‐Yun Sung |
author_sort | Hsi‐Chin Hsin |
collection | DOAJ |
description | Inverse texture synthesis (ITS) plays an important role in many computer vision applications. It aims at generating small compaction images to capture significant features of textures, from which arbitrarily large images with similar textures can be re‐synthesised. This study presents a fast approach to ITS with two algorithms developed in hierarchical wavelet packet (WP) trees: the modified inverse texture synthesis (MITS) algorithm, which extends the ITS algorithm into the WP domain, and the wavelet‐packet‐tree‐based cropping (WPTC) algorithm for the initialisation of MITS. Experimental results show that the combination of WPTC and MITS termed the image compaction in wavelet packet trees algorithm outperforms the ITS algorithm in terms of the ‘peak signal‐to‐noise ratio’ and computation time. |
first_indexed | 2024-03-12T00:36:14Z |
format | Article |
id | doaj.art-813df41dea694a84b3f77c2dd393a6f5 |
institution | Directory Open Access Journal |
issn | 1751-9632 1751-9640 |
language | English |
last_indexed | 2024-03-12T00:36:14Z |
publishDate | 2015-04-01 |
publisher | Wiley |
record_format | Article |
series | IET Computer Vision |
spelling | doaj.art-813df41dea694a84b3f77c2dd393a6f52023-09-15T09:37:33ZengWileyIET Computer Vision1751-96321751-96402015-04-019219820710.1049/iet-cvi.2013.0262Inverse texture synthesis in wavelet packet treesHsi‐Chin Hsin0Tze‐Yun Sung1Department of Computer Science and Information EngineeringNational United UniversityMiaoli36003TaiwanDepartment of Electronics EngineeringChung‐Hua UniversityHsinchuTaiwanInverse texture synthesis (ITS) plays an important role in many computer vision applications. It aims at generating small compaction images to capture significant features of textures, from which arbitrarily large images with similar textures can be re‐synthesised. This study presents a fast approach to ITS with two algorithms developed in hierarchical wavelet packet (WP) trees: the modified inverse texture synthesis (MITS) algorithm, which extends the ITS algorithm into the WP domain, and the wavelet‐packet‐tree‐based cropping (WPTC) algorithm for the initialisation of MITS. Experimental results show that the combination of WPTC and MITS termed the image compaction in wavelet packet trees algorithm outperforms the ITS algorithm in terms of the ‘peak signal‐to‐noise ratio’ and computation time.https://doi.org/10.1049/iet-cvi.2013.0262computer vision applicationstexture featureshierarchical wavelet packetWP treesmodified inverse texture synthesisMITS algorithm |
spellingShingle | Hsi‐Chin Hsin Tze‐Yun Sung Inverse texture synthesis in wavelet packet trees IET Computer Vision computer vision applications texture features hierarchical wavelet packet WP trees modified inverse texture synthesis MITS algorithm |
title | Inverse texture synthesis in wavelet packet trees |
title_full | Inverse texture synthesis in wavelet packet trees |
title_fullStr | Inverse texture synthesis in wavelet packet trees |
title_full_unstemmed | Inverse texture synthesis in wavelet packet trees |
title_short | Inverse texture synthesis in wavelet packet trees |
title_sort | inverse texture synthesis in wavelet packet trees |
topic | computer vision applications texture features hierarchical wavelet packet WP trees modified inverse texture synthesis MITS algorithm |
url | https://doi.org/10.1049/iet-cvi.2013.0262 |
work_keys_str_mv | AT hsichinhsin inversetexturesynthesisinwaveletpackettrees AT tzeyunsung inversetexturesynthesisinwaveletpackettrees |