VECTORIZING IMAGES OF ANY SIZE

Yuchen He; Sung Ha Kang; Jean-Michel Morel

doi:10.1109/ICIP46576.2022.9897200

VECTORIZING IMAGES OF ANY SIZE

Yuchen He
, Sung Ha Kang
, Jean-Michel Morel

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

5 Citations (Scopus)

Abstract

We propose a novel algorithm for converting quantized raster color images to resolution-independent scalable vector graphics (SVG). Starting from the discontinuity set of the input image, the algorithm connects the pieces of curves separating two constant regions to reconstruct the apparent contours of objects and interpret T-junctions and saddle points. This structure is depixelized by curve affine shortening, which requires maintaining the topology of the discontinuity set during filtering. The resulting Hierarchical Curve-based Vectorization (HCV) algorithm compares favorably to several state-of-art vectorization algorithms and software for color-quantized photos and pixel art. © 2022 IEEE.

Original language	English
Title of host publication	2022 IEEE International Conference on Image Processing - Proceedings
Publisher	IEEE
Pages	816-820
ISBN (Electronic)	978-1-6654-9620-9
ISBN (Print)	978-1-6654-9621-6
DOIs	https://doi.org/10.1109/ICIP46576.2022.9897200
Publication status	Published - 2022
Externally published	Yes
Event	29th IEEE International Conference on Image Processing (ICIP 2022) - Virtual, Bordeaux, France Duration: 16 Oct 2022 → 19 Oct 2022 https://2022.ieeeicip.org/

Publication series

Name	Proceedings - International Conference on Image Processing, ICIP
ISSN (Print)	1522-4880
ISSN (Electronic)	2381-8549

Conference

Conference	29th IEEE International Conference on Image Processing (ICIP 2022)
Place	France
City	Bordeaux
Period	16/10/22 → 19/10/22
Internet address	https://2022.ieeeicip.org/

Research Keywords

Affine scale-space
Bézier curve
Color image
Vectorization

Access Output

10.1109/ICIP46576.2022.9897200

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{da5ab9e7a63142508e4e2a4f77bcaa43,

title = "VECTORIZING IMAGES OF ANY SIZE",

abstract = "We propose a novel algorithm for converting quantized raster color images to resolution-independent scalable vector graphics (SVG). Starting from the discontinuity set of the input image, the algorithm connects the pieces of curves separating two constant regions to reconstruct the apparent contours of objects and interpret T-junctions and saddle points. This structure is depixelized by curve affine shortening, which requires maintaining the topology of the discontinuity set during filtering. The resulting Hierarchical Curve-based Vectorization (HCV) algorithm compares favorably to several state-of-art vectorization algorithms and software for color-quantized photos and pixel art. {\textcopyright} 2022 IEEE.",

keywords = "Affine scale-space, B{\'e}zier curve, Color image, Vectorization",

author = "Yuchen He and Kang, \{Sung Ha\} and Jean-Michel Morel",

year = "2022",

doi = "10.1109/ICIP46576.2022.9897200",

language = "English",

isbn = "978-1-6654-9621-6",

series = "Proceedings - International Conference on Image Processing, ICIP",

publisher = "IEEE",

pages = "816--820",

booktitle = "2022 IEEE International Conference on Image Processing - Proceedings",

address = "United States",

note = "29th IEEE International Conference on Image Processing (ICIP 2022) ; Conference date: 16-10-2022 Through 19-10-2022",

url = "https://2022.ieeeicip.org/",

}

VECTORIZING IMAGES OF ANY SIZE. / He, Yuchen; Kang, Sung Ha; Morel, Jean-Michel.
2022 IEEE International Conference on Image Processing - Proceedings. IEEE, 2022. p. 816-820 (Proceedings - International Conference on Image Processing, ICIP).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - VECTORIZING IMAGES OF ANY SIZE

AU - He, Yuchen

AU - Kang, Sung Ha

AU - Morel, Jean-Michel

PY - 2022

Y1 - 2022

N2 - We propose a novel algorithm for converting quantized raster color images to resolution-independent scalable vector graphics (SVG). Starting from the discontinuity set of the input image, the algorithm connects the pieces of curves separating two constant regions to reconstruct the apparent contours of objects and interpret T-junctions and saddle points. This structure is depixelized by curve affine shortening, which requires maintaining the topology of the discontinuity set during filtering. The resulting Hierarchical Curve-based Vectorization (HCV) algorithm compares favorably to several state-of-art vectorization algorithms and software for color-quantized photos and pixel art. © 2022 IEEE.

AB - We propose a novel algorithm for converting quantized raster color images to resolution-independent scalable vector graphics (SVG). Starting from the discontinuity set of the input image, the algorithm connects the pieces of curves separating two constant regions to reconstruct the apparent contours of objects and interpret T-junctions and saddle points. This structure is depixelized by curve affine shortening, which requires maintaining the topology of the discontinuity set during filtering. The resulting Hierarchical Curve-based Vectorization (HCV) algorithm compares favorably to several state-of-art vectorization algorithms and software for color-quantized photos and pixel art. © 2022 IEEE.

KW - Affine scale-space

KW - Bézier curve

KW - Color image

KW - Vectorization

UR - https://www.scopus.com/pages/publications/85136628768

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85136628768&origin=recordpage

U2 - 10.1109/ICIP46576.2022.9897200

DO - 10.1109/ICIP46576.2022.9897200

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 978-1-6654-9621-6

T3 - Proceedings - International Conference on Image Processing, ICIP

SP - 816

EP - 820

BT - 2022 IEEE International Conference on Image Processing - Proceedings

PB - IEEE

T2 - 29th IEEE International Conference on Image Processing (ICIP 2022)

Y2 - 16 October 2022 through 19 October 2022

ER -

VECTORIZING IMAGES OF ANY SIZE

Abstract

Publication series

Conference

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this