Query-by-Sketch Based Image Synthesis

David GAVILAN; Suguru SAITO; Masayuki NAKAJIMA

doi:10.1093/ietisy/e91-d.9.2341

Query-by-Sketch Based Image Synthesis

David GAVILAN, Suguru SAITO, Masayuki NAKAJIMA

Full Text Views

0

Cite this

Summary :

Using query-by-sketch we propose an application to efficiently create collages with some user interaction. Using rough color strokes that represent the target collage, images are automatically retrieved and segmented to create a seamless collage. The database is indexed using simple geometrical and color features for each region, and histograms that represent these features for each image. The image collection is then queried by means of a simple paint tool. The individual segments retrieved are added to the collage using Poisson image editing or alpha matting. The user is able to modify the default segmentations interactively, as well as the position, scale, and blending options for each object. The resulting collage can then be used as an input query to find other relevant images from the database.

Publication: IEICE TRANSACTIONS on Information Vol.E91-D No.9 pp.2341-2352

Publication Date: 2008/09/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1093/ietisy/e91-d.9.2341

Type of Manuscript: PAPER

Category: Image Processing and Video Processing

Cite this

Copy

David GAVILAN, Suguru SAITO, Masayuki NAKAJIMA, "Query-by-Sketch Based Image Synthesis" in IEICE TRANSACTIONS on Information, vol. E91-D, no. 9, pp. 2341-2352, September 2008, doi: 10.1093/ietisy/e91-d.9.2341.
Abstract: Using query-by-sketch we propose an application to efficiently create collages with some user interaction. Using rough color strokes that represent the target collage, images are automatically retrieved and segmented to create a seamless collage. The database is indexed using simple geometrical and color features for each region, and histograms that represent these features for each image. The image collection is then queried by means of a simple paint tool. The individual segments retrieved are added to the collage using Poisson image editing or alpha matting. The user is able to modify the default segmentations interactively, as well as the position, scale, and blending options for each object. The resulting collage can then be used as an input query to find other relevant images from the database.
URL: https://global.ieice.org/en_transactions/information/10.1093/ietisy/e91-d.9.2341/_p

Copy

@ARTICLE{e91-d_9_2341,
author={David GAVILAN, Suguru SAITO, Masayuki NAKAJIMA, },
journal={IEICE TRANSACTIONS on Information},
title={Query-by-Sketch Based Image Synthesis},
year={2008},
volume={E91-D},
number={9},
pages={2341-2352},
abstract={Using query-by-sketch we propose an application to efficiently create collages with some user interaction. Using rough color strokes that represent the target collage, images are automatically retrieved and segmented to create a seamless collage. The database is indexed using simple geometrical and color features for each region, and histograms that represent these features for each image. The image collection is then queried by means of a simple paint tool. The individual segments retrieved are added to the collage using Poisson image editing or alpha matting. The user is able to modify the default segmentations interactively, as well as the position, scale, and blending options for each object. The resulting collage can then be used as an input query to find other relevant images from the database.},
keywords={},
doi={10.1093/ietisy/e91-d.9.2341},
ISSN={1745-1361},
month={September},}

Copy

TY - JOUR
TI - Query-by-Sketch Based Image Synthesis
T2 - IEICE TRANSACTIONS on Information
SP - 2341
EP - 2352
AU - David GAVILAN
AU - Suguru SAITO
AU - Masayuki NAKAJIMA
PY - 2008
DO - 10.1093/ietisy/e91-d.9.2341
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E91-D
IS - 9
JA - IEICE TRANSACTIONS on Information
Y1 - September 2008
AB - Using query-by-sketch we propose an application to efficiently create collages with some user interaction. Using rough color strokes that represent the target collage, images are automatically retrieved and segmented to create a seamless collage. The database is indexed using simple geometrical and color features for each region, and histograms that represent these features for each image. The image collection is then queried by means of a simple paint tool. The individual segments retrieved are added to the collage using Poisson image editing or alpha matting. The user is able to modify the default segmentations interactively, as well as the position, scale, and blending options for each object. The resulting collage can then be used as an input query to find other relevant images from the database.
ER -