Adaptively tiled image mosaics utilizing measures of color and region entropy

Lina Zhang, Kwan-Liu Ma, Jinhui Yu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Image mosaicing involves splitting an input image into a set of tiles, then replacing each tile with another image from a large dataset so that, when viewed from a distance, the resulting image resembles the original. We present a new approach for generating image mosaics using variable sized tiles made up from patches taken from photographs, paintings and texture images. This is difierent from previous work, where either simple regular tiling or adaptive tiling based on variations of RGB color was used. We propose an adaptive tiling theme by means of region entropy. In order to avoid the mismatch in roughness between the sub-image in the tile region of the input image and tile images in the dataset that may arise in the previous RGB color based image descriptors, we introduce the region entropy into the image descriptor to achieve better matching in both color and roughness. We also propose a new metric to measure the quality of the image mosaic which takes both the similarity and the mutual information between the generated mosaics and input images into account. The final mosaic images in this work are obtained by optimizing an objective function based on this metric.

Original languageEnglish (US)
Title of host publicationVINCI 2016 - 9th International Symposium on Visual Information Communication and Interaction
EditorsKang Zhang, Andreas Kerren
PublisherAssociation for Computing Machinery
Pages122-129
Number of pages8
ISBN (Electronic)9781450341493
DOIs
StatePublished - Sep 24 2016
Event9th International Symposium on Visual Information Communication and Interaction, VINCI 2016 - Dallas, United States
Duration: Sep 24 2016Sep 26 2016

Other

Other9th International Symposium on Visual Information Communication and Interaction, VINCI 2016
CountryUnited States
CityDallas
Period9/24/169/26/16

Fingerprint

Tile
Entropy
Color
Surface roughness
Painting
Textures

Keywords

  • Entropy
  • Information evaluation
  • Mosaic
  • Tiling

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Computer Networks and Communications
  • Computer Vision and Pattern Recognition
  • Software

Cite this

Zhang, L., Ma, K-L., & Yu, J. (2016). Adaptively tiled image mosaics utilizing measures of color and region entropy. In K. Zhang, & A. Kerren (Eds.), VINCI 2016 - 9th International Symposium on Visual Information Communication and Interaction (pp. 122-129). Association for Computing Machinery. https://doi.org/10.1145/2968220.2968228

Adaptively tiled image mosaics utilizing measures of color and region entropy. / Zhang, Lina; Ma, Kwan-Liu; Yu, Jinhui.

VINCI 2016 - 9th International Symposium on Visual Information Communication and Interaction. ed. / Kang Zhang; Andreas Kerren. Association for Computing Machinery, 2016. p. 122-129.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Zhang, L, Ma, K-L & Yu, J 2016, Adaptively tiled image mosaics utilizing measures of color and region entropy. in K Zhang & A Kerren (eds), VINCI 2016 - 9th International Symposium on Visual Information Communication and Interaction. Association for Computing Machinery, pp. 122-129, 9th International Symposium on Visual Information Communication and Interaction, VINCI 2016, Dallas, United States, 9/24/16. https://doi.org/10.1145/2968220.2968228
Zhang L, Ma K-L, Yu J. Adaptively tiled image mosaics utilizing measures of color and region entropy. In Zhang K, Kerren A, editors, VINCI 2016 - 9th International Symposium on Visual Information Communication and Interaction. Association for Computing Machinery. 2016. p. 122-129 https://doi.org/10.1145/2968220.2968228
Zhang, Lina ; Ma, Kwan-Liu ; Yu, Jinhui. / Adaptively tiled image mosaics utilizing measures of color and region entropy. VINCI 2016 - 9th International Symposium on Visual Information Communication and Interaction. editor / Kang Zhang ; Andreas Kerren. Association for Computing Machinery, 2016. pp. 122-129
@inproceedings{6f3b4b6a3a8e4c75b0fa75c40343aa33,
title = "Adaptively tiled image mosaics utilizing measures of color and region entropy",
abstract = "Image mosaicing involves splitting an input image into a set of tiles, then replacing each tile with another image from a large dataset so that, when viewed from a distance, the resulting image resembles the original. We present a new approach for generating image mosaics using variable sized tiles made up from patches taken from photographs, paintings and texture images. This is difierent from previous work, where either simple regular tiling or adaptive tiling based on variations of RGB color was used. We propose an adaptive tiling theme by means of region entropy. In order to avoid the mismatch in roughness between the sub-image in the tile region of the input image and tile images in the dataset that may arise in the previous RGB color based image descriptors, we introduce the region entropy into the image descriptor to achieve better matching in both color and roughness. We also propose a new metric to measure the quality of the image mosaic which takes both the similarity and the mutual information between the generated mosaics and input images into account. The final mosaic images in this work are obtained by optimizing an objective function based on this metric.",
keywords = "Entropy, Information evaluation, Mosaic, Tiling",
author = "Lina Zhang and Kwan-Liu Ma and Jinhui Yu",
year = "2016",
month = "9",
day = "24",
doi = "10.1145/2968220.2968228",
language = "English (US)",
pages = "122--129",
editor = "Kang Zhang and Andreas Kerren",
booktitle = "VINCI 2016 - 9th International Symposium on Visual Information Communication and Interaction",
publisher = "Association for Computing Machinery",

}

TY - GEN

T1 - Adaptively tiled image mosaics utilizing measures of color and region entropy

AU - Zhang, Lina

AU - Ma, Kwan-Liu

AU - Yu, Jinhui

PY - 2016/9/24

Y1 - 2016/9/24

N2 - Image mosaicing involves splitting an input image into a set of tiles, then replacing each tile with another image from a large dataset so that, when viewed from a distance, the resulting image resembles the original. We present a new approach for generating image mosaics using variable sized tiles made up from patches taken from photographs, paintings and texture images. This is difierent from previous work, where either simple regular tiling or adaptive tiling based on variations of RGB color was used. We propose an adaptive tiling theme by means of region entropy. In order to avoid the mismatch in roughness between the sub-image in the tile region of the input image and tile images in the dataset that may arise in the previous RGB color based image descriptors, we introduce the region entropy into the image descriptor to achieve better matching in both color and roughness. We also propose a new metric to measure the quality of the image mosaic which takes both the similarity and the mutual information between the generated mosaics and input images into account. The final mosaic images in this work are obtained by optimizing an objective function based on this metric.

AB - Image mosaicing involves splitting an input image into a set of tiles, then replacing each tile with another image from a large dataset so that, when viewed from a distance, the resulting image resembles the original. We present a new approach for generating image mosaics using variable sized tiles made up from patches taken from photographs, paintings and texture images. This is difierent from previous work, where either simple regular tiling or adaptive tiling based on variations of RGB color was used. We propose an adaptive tiling theme by means of region entropy. In order to avoid the mismatch in roughness between the sub-image in the tile region of the input image and tile images in the dataset that may arise in the previous RGB color based image descriptors, we introduce the region entropy into the image descriptor to achieve better matching in both color and roughness. We also propose a new metric to measure the quality of the image mosaic which takes both the similarity and the mutual information between the generated mosaics and input images into account. The final mosaic images in this work are obtained by optimizing an objective function based on this metric.

KW - Entropy

KW - Information evaluation

KW - Mosaic

KW - Tiling

UR - http://www.scopus.com/inward/record.url?scp=85010957439&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85010957439&partnerID=8YFLogxK

U2 - 10.1145/2968220.2968228

DO - 10.1145/2968220.2968228

M3 - Conference contribution

AN - SCOPUS:85010957439

SP - 122

EP - 129

BT - VINCI 2016 - 9th International Symposium on Visual Information Communication and Interaction

A2 - Zhang, Kang

A2 - Kerren, Andreas

PB - Association for Computing Machinery

ER -