Spatial stimuli gradient sketch model

Joshin John Mathew, Alex Pappachen James

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

The inability of automated edge detection methods inspired from primal sketch models to accurately calculate object edges under the influence of pixel noise is an open problem. Extending the principles of image perception i.e. Weber-Fechner law, and Sheperd similarity law, we propose a new edge detection method and formulation that use perceived brightness and neighbourhood similarity calculations in the determination of robust object edges. The robustness of the detected edges is benchmark against Sobel, SIS, Kirsch, and Prewitt edge detection methods in an example face recognition problem showing statistically significant improvement in recognition accuracy and pixel noise tolerance.

Original languageEnglish
Article number7045586
Pages (from-to)1336-1339
Number of pages4
JournalIEEE Signal Processing Letters
Volume22
Issue number9
DOIs
Publication statusPublished - Sep 1 2015

Fingerprint

Edge Detection
Edge detection
Gradient
Pixel
Pixels
Brightness
Face recognition
Face Recognition
Tolerance
Luminance
Open Problems
Model
Benchmark
Robustness
Calculate
Formulation
Object
Similarity

Keywords

  • Edge detection
  • local stimuli
  • perceived brightness
  • primal sketch model

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Signal Processing
  • Applied Mathematics

Cite this

Spatial stimuli gradient sketch model. / Mathew, Joshin John; James, Alex Pappachen.

In: IEEE Signal Processing Letters, Vol. 22, No. 9, 7045586, 01.09.2015, p. 1336-1339.

Research output: Contribution to journalArticle

Mathew, Joshin John ; James, Alex Pappachen. / Spatial stimuli gradient sketch model. In: IEEE Signal Processing Letters. 2015 ; Vol. 22, No. 9. pp. 1336-1339.
@article{2330251f02744f5a804339a847f29f68,
title = "Spatial stimuli gradient sketch model",
abstract = "The inability of automated edge detection methods inspired from primal sketch models to accurately calculate object edges under the influence of pixel noise is an open problem. Extending the principles of image perception i.e. Weber-Fechner law, and Sheperd similarity law, we propose a new edge detection method and formulation that use perceived brightness and neighbourhood similarity calculations in the determination of robust object edges. The robustness of the detected edges is benchmark against Sobel, SIS, Kirsch, and Prewitt edge detection methods in an example face recognition problem showing statistically significant improvement in recognition accuracy and pixel noise tolerance.",
keywords = "Edge detection, local stimuli, perceived brightness, primal sketch model",
author = "Mathew, {Joshin John} and James, {Alex Pappachen}",
year = "2015",
month = "9",
day = "1",
doi = "10.1109/LSP.2015.2404827",
language = "English",
volume = "22",
pages = "1336--1339",
journal = "IEEE Signal Processing Letters",
issn = "1070-9908",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "9",

}

TY - JOUR

T1 - Spatial stimuli gradient sketch model

AU - Mathew, Joshin John

AU - James, Alex Pappachen

PY - 2015/9/1

Y1 - 2015/9/1

N2 - The inability of automated edge detection methods inspired from primal sketch models to accurately calculate object edges under the influence of pixel noise is an open problem. Extending the principles of image perception i.e. Weber-Fechner law, and Sheperd similarity law, we propose a new edge detection method and formulation that use perceived brightness and neighbourhood similarity calculations in the determination of robust object edges. The robustness of the detected edges is benchmark against Sobel, SIS, Kirsch, and Prewitt edge detection methods in an example face recognition problem showing statistically significant improvement in recognition accuracy and pixel noise tolerance.

AB - The inability of automated edge detection methods inspired from primal sketch models to accurately calculate object edges under the influence of pixel noise is an open problem. Extending the principles of image perception i.e. Weber-Fechner law, and Sheperd similarity law, we propose a new edge detection method and formulation that use perceived brightness and neighbourhood similarity calculations in the determination of robust object edges. The robustness of the detected edges is benchmark against Sobel, SIS, Kirsch, and Prewitt edge detection methods in an example face recognition problem showing statistically significant improvement in recognition accuracy and pixel noise tolerance.

KW - Edge detection

KW - local stimuli

KW - perceived brightness

KW - primal sketch model

UR - http://www.scopus.com/inward/record.url?scp=84923320895&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84923320895&partnerID=8YFLogxK

U2 - 10.1109/LSP.2015.2404827

DO - 10.1109/LSP.2015.2404827

M3 - Article

VL - 22

SP - 1336

EP - 1339

JO - IEEE Signal Processing Letters

JF - IEEE Signal Processing Letters

SN - 1070-9908

IS - 9

M1 - 7045586

ER -