Interval HSV: Extracting ink annotations

John C. Femiani, Anshuman Razdan

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

6 Citations (Scopus)

Abstract

The HSV color space is an intuitive way to reason about color, but the nonlinear relationship to RGB co-ordinates complicates histogram analysis of colors in HSV. We present novel Interval-HSV formulas to identify a range in HSV for each RGB interval. We show the usefulness by introducing a parameter-free and completely automatic technique to extract both colored and black ink annotations from faded backgrounds such as digitized aerial photographs, maps, or printed-text documents. We discuss the characteristics of ink mixing in the HSV color space and discover a single feature, the upper limit of the saturation-interval, to extract ink even when it is achromatic. We form robust Interval-HV histograms in order to identify the number and colors of inks in the image.

Original languageEnglish (US)
Title of host publication2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009
Pages2520-2527
Number of pages8
DOIs
StatePublished - 2009
Event2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009 - Miami, FL, United States
Duration: Jun 20 2009Jun 25 2009

Other

Other2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009
CountryUnited States
CityMiami, FL
Period6/20/096/25/09

Fingerprint

Ink
Color
Antennas

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Biomedical Engineering

Cite this

Femiani, J. C., & Razdan, A. (2009). Interval HSV: Extracting ink annotations. In 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009 (pp. 2520-2527). [5206554] https://doi.org/10.1109/CVPRW.2009.5206554

Interval HSV : Extracting ink annotations. / Femiani, John C.; Razdan, Anshuman.

2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009. 2009. p. 2520-2527 5206554.

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

Femiani, JC & Razdan, A 2009, Interval HSV: Extracting ink annotations. in 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009., 5206554, pp. 2520-2527, 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009, Miami, FL, United States, 6/20/09. https://doi.org/10.1109/CVPRW.2009.5206554
Femiani JC, Razdan A. Interval HSV: Extracting ink annotations. In 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009. 2009. p. 2520-2527. 5206554 https://doi.org/10.1109/CVPRW.2009.5206554
Femiani, John C. ; Razdan, Anshuman. / Interval HSV : Extracting ink annotations. 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009. 2009. pp. 2520-2527
@inproceedings{b8db0911aaa34674abd5b625f16205e5,
title = "Interval HSV: Extracting ink annotations",
abstract = "The HSV color space is an intuitive way to reason about color, but the nonlinear relationship to RGB co-ordinates complicates histogram analysis of colors in HSV. We present novel Interval-HSV formulas to identify a range in HSV for each RGB interval. We show the usefulness by introducing a parameter-free and completely automatic technique to extract both colored and black ink annotations from faded backgrounds such as digitized aerial photographs, maps, or printed-text documents. We discuss the characteristics of ink mixing in the HSV color space and discover a single feature, the upper limit of the saturation-interval, to extract ink even when it is achromatic. We form robust Interval-HV histograms in order to identify the number and colors of inks in the image.",
author = "Femiani, {John C.} and Anshuman Razdan",
year = "2009",
doi = "10.1109/CVPRW.2009.5206554",
language = "English (US)",
isbn = "9781424439935",
pages = "2520--2527",
booktitle = "2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009",

}

TY - GEN

T1 - Interval HSV

T2 - Extracting ink annotations

AU - Femiani, John C.

AU - Razdan, Anshuman

PY - 2009

Y1 - 2009

N2 - The HSV color space is an intuitive way to reason about color, but the nonlinear relationship to RGB co-ordinates complicates histogram analysis of colors in HSV. We present novel Interval-HSV formulas to identify a range in HSV for each RGB interval. We show the usefulness by introducing a parameter-free and completely automatic technique to extract both colored and black ink annotations from faded backgrounds such as digitized aerial photographs, maps, or printed-text documents. We discuss the characteristics of ink mixing in the HSV color space and discover a single feature, the upper limit of the saturation-interval, to extract ink even when it is achromatic. We form robust Interval-HV histograms in order to identify the number and colors of inks in the image.

AB - The HSV color space is an intuitive way to reason about color, but the nonlinear relationship to RGB co-ordinates complicates histogram analysis of colors in HSV. We present novel Interval-HSV formulas to identify a range in HSV for each RGB interval. We show the usefulness by introducing a parameter-free and completely automatic technique to extract both colored and black ink annotations from faded backgrounds such as digitized aerial photographs, maps, or printed-text documents. We discuss the characteristics of ink mixing in the HSV color space and discover a single feature, the upper limit of the saturation-interval, to extract ink even when it is achromatic. We form robust Interval-HV histograms in order to identify the number and colors of inks in the image.

UR - http://www.scopus.com/inward/record.url?scp=70450245509&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70450245509&partnerID=8YFLogxK

U2 - 10.1109/CVPRW.2009.5206554

DO - 10.1109/CVPRW.2009.5206554

M3 - Conference contribution

AN - SCOPUS:70450245509

SN - 9781424439935

SP - 2520

EP - 2527

BT - 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009

ER -