Fast histogram equalization for medical image enhancement

Qian Wang, Liya Chen, Dinggang Shen

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

28 Citations (Scopus)

Abstract

To overcome the problem that the histogram equalization can fail for discrete images, a local-mean based strict pixel ordering method has been proposed recently, although it is unpractical for 3D medical image enhancement due to its complex computation. In this paper, a novel histogram mapping method is proposed. It uses a fast local feature generation technique to establish a combined histogram that represents voxels' local means as well as grey levels. Different sections of the combined histogram, separated by individual peaks, are independently mapped into the target histogram scale under the constraint that the final overall histogram should be as uniform as possible. By using this method, the speed of histogram equalization is dramatically improved, and the satisfactory enhancement results are also achieved.

Original languageEnglish
Title of host publicationProceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - "Personalized Healthcare through Technology"
Pages2217-2220
Number of pages4
Publication statusPublished - 2008 Dec 1
Externally publishedYes
Event30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - Vancouver, BC, Canada
Duration: 2008 Aug 202008 Aug 25

Other

Other30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08
CountryCanada
CityVancouver, BC
Period08/8/2008/8/25

Fingerprint

Image Enhancement
Image enhancement
Pixels

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Biomedical Engineering
  • Health Informatics

Cite this

Wang, Q., Chen, L., & Shen, D. (2008). Fast histogram equalization for medical image enhancement. In Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - "Personalized Healthcare through Technology" (pp. 2217-2220). [4649636]

Fast histogram equalization for medical image enhancement. / Wang, Qian; Chen, Liya; Shen, Dinggang.

Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - "Personalized Healthcare through Technology". 2008. p. 2217-2220 4649636.

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

Wang, Q, Chen, L & Shen, D 2008, Fast histogram equalization for medical image enhancement. in Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - "Personalized Healthcare through Technology"., 4649636, pp. 2217-2220, 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08, Vancouver, BC, Canada, 08/8/20.
Wang Q, Chen L, Shen D. Fast histogram equalization for medical image enhancement. In Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - "Personalized Healthcare through Technology". 2008. p. 2217-2220. 4649636
Wang, Qian ; Chen, Liya ; Shen, Dinggang. / Fast histogram equalization for medical image enhancement. Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - "Personalized Healthcare through Technology". 2008. pp. 2217-2220
@inproceedings{ce5c92146f3c4985ab12dc8ab6951a9a,
title = "Fast histogram equalization for medical image enhancement",
abstract = "To overcome the problem that the histogram equalization can fail for discrete images, a local-mean based strict pixel ordering method has been proposed recently, although it is unpractical for 3D medical image enhancement due to its complex computation. In this paper, a novel histogram mapping method is proposed. It uses a fast local feature generation technique to establish a combined histogram that represents voxels' local means as well as grey levels. Different sections of the combined histogram, separated by individual peaks, are independently mapped into the target histogram scale under the constraint that the final overall histogram should be as uniform as possible. By using this method, the speed of histogram equalization is dramatically improved, and the satisfactory enhancement results are also achieved.",
author = "Qian Wang and Liya Chen and Dinggang Shen",
year = "2008",
month = "12",
day = "1",
language = "English",
isbn = "9781424418152",
pages = "2217--2220",
booktitle = "Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - {"}Personalized Healthcare through Technology{"}",

}

TY - GEN

T1 - Fast histogram equalization for medical image enhancement

AU - Wang, Qian

AU - Chen, Liya

AU - Shen, Dinggang

PY - 2008/12/1

Y1 - 2008/12/1

N2 - To overcome the problem that the histogram equalization can fail for discrete images, a local-mean based strict pixel ordering method has been proposed recently, although it is unpractical for 3D medical image enhancement due to its complex computation. In this paper, a novel histogram mapping method is proposed. It uses a fast local feature generation technique to establish a combined histogram that represents voxels' local means as well as grey levels. Different sections of the combined histogram, separated by individual peaks, are independently mapped into the target histogram scale under the constraint that the final overall histogram should be as uniform as possible. By using this method, the speed of histogram equalization is dramatically improved, and the satisfactory enhancement results are also achieved.

AB - To overcome the problem that the histogram equalization can fail for discrete images, a local-mean based strict pixel ordering method has been proposed recently, although it is unpractical for 3D medical image enhancement due to its complex computation. In this paper, a novel histogram mapping method is proposed. It uses a fast local feature generation technique to establish a combined histogram that represents voxels' local means as well as grey levels. Different sections of the combined histogram, separated by individual peaks, are independently mapped into the target histogram scale under the constraint that the final overall histogram should be as uniform as possible. By using this method, the speed of histogram equalization is dramatically improved, and the satisfactory enhancement results are also achieved.

UR - http://www.scopus.com/inward/record.url?scp=61849175469&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=61849175469&partnerID=8YFLogxK

M3 - Conference contribution

C2 - 19163139

AN - SCOPUS:61849175469

SN - 9781424418152

SP - 2217

EP - 2220

BT - Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - "Personalized Healthcare through Technology"

ER -