A log-ratio pair approach to endoscopic image matching

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

3 Citations (Scopus)

Abstract

In this paper, we proposed a novel algorithm for endoscopic image matching. The algorithm consists of two main components, log-ratio descriptor and probabilistic matching criterion. Log-ratio descriptor is developed by using selected pair of grayscale intensity information that surround the keypoint. The spatial distribution of the pairs follow approximately normal distribution. Then, probabilistic t-test is implemented to produce a distinctive features descriptor. Acceptable probability is calculated based on the probability of t-distribution information. Finally, matching the keypoints is performed by comparing the acceptable probability and nearest neighbor location information. Simulation results show that the proposed algorithm achieves more than 90% matching in various types of tissue surface and movement.

Original languageEnglish
Title of host publicationIEEE Workshop on Statistical Signal Processing Proceedings
PublisherIEEE Computer Society
Pages185-188
Number of pages4
ISBN (Print)9781479949755
DOIs
Publication statusPublished - 2014
Event2014 IEEE Workshop on Statistical Signal Processing, SSP 2014 - Gold Coast, QLD
Duration: 29 Jun 20142 Jul 2014

Other

Other2014 IEEE Workshop on Statistical Signal Processing, SSP 2014
CityGold Coast, QLD
Period29/6/142/7/14

Fingerprint

Image matching
Image Matching
Descriptors
t-distribution
t-test
Normal distribution
Spatial Distribution
Spatial distribution
Gaussian distribution
Nearest Neighbor
Tissue
Simulation

Keywords

  • endoscopic image
  • log ratio descriptor
  • matching keypoint

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Applied Mathematics
  • Signal Processing
  • Computer Science Applications

Cite this

Karim, R. A., Mustafa, M. M., & Zulkifley, M. A. (2014). A log-ratio pair approach to endoscopic image matching. In IEEE Workshop on Statistical Signal Processing Proceedings (pp. 185-188). [6884606] IEEE Computer Society. https://doi.org/10.1109/SSP.2014.6884606

A log-ratio pair approach to endoscopic image matching. / Karim, Rohana Abdul; Mustafa, Mohd. Marzuki; Zulkifley, Mohd Asyraf.

IEEE Workshop on Statistical Signal Processing Proceedings. IEEE Computer Society, 2014. p. 185-188 6884606.

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

Karim, RA, Mustafa, MM & Zulkifley, MA 2014, A log-ratio pair approach to endoscopic image matching. in IEEE Workshop on Statistical Signal Processing Proceedings., 6884606, IEEE Computer Society, pp. 185-188, 2014 IEEE Workshop on Statistical Signal Processing, SSP 2014, Gold Coast, QLD, 29/6/14. https://doi.org/10.1109/SSP.2014.6884606
Karim RA, Mustafa MM, Zulkifley MA. A log-ratio pair approach to endoscopic image matching. In IEEE Workshop on Statistical Signal Processing Proceedings. IEEE Computer Society. 2014. p. 185-188. 6884606 https://doi.org/10.1109/SSP.2014.6884606
Karim, Rohana Abdul ; Mustafa, Mohd. Marzuki ; Zulkifley, Mohd Asyraf. / A log-ratio pair approach to endoscopic image matching. IEEE Workshop on Statistical Signal Processing Proceedings. IEEE Computer Society, 2014. pp. 185-188
@inproceedings{b30e7251300f443b9eb69bdf5b6b6217,
title = "A log-ratio pair approach to endoscopic image matching",
abstract = "In this paper, we proposed a novel algorithm for endoscopic image matching. The algorithm consists of two main components, log-ratio descriptor and probabilistic matching criterion. Log-ratio descriptor is developed by using selected pair of grayscale intensity information that surround the keypoint. The spatial distribution of the pairs follow approximately normal distribution. Then, probabilistic t-test is implemented to produce a distinctive features descriptor. Acceptable probability is calculated based on the probability of t-distribution information. Finally, matching the keypoints is performed by comparing the acceptable probability and nearest neighbor location information. Simulation results show that the proposed algorithm achieves more than 90{\%} matching in various types of tissue surface and movement.",
keywords = "endoscopic image, log ratio descriptor, matching keypoint",
author = "Karim, {Rohana Abdul} and Mustafa, {Mohd. Marzuki} and Zulkifley, {Mohd Asyraf}",
year = "2014",
doi = "10.1109/SSP.2014.6884606",
language = "English",
isbn = "9781479949755",
pages = "185--188",
booktitle = "IEEE Workshop on Statistical Signal Processing Proceedings",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - A log-ratio pair approach to endoscopic image matching

AU - Karim, Rohana Abdul

AU - Mustafa, Mohd. Marzuki

AU - Zulkifley, Mohd Asyraf

PY - 2014

Y1 - 2014

N2 - In this paper, we proposed a novel algorithm for endoscopic image matching. The algorithm consists of two main components, log-ratio descriptor and probabilistic matching criterion. Log-ratio descriptor is developed by using selected pair of grayscale intensity information that surround the keypoint. The spatial distribution of the pairs follow approximately normal distribution. Then, probabilistic t-test is implemented to produce a distinctive features descriptor. Acceptable probability is calculated based on the probability of t-distribution information. Finally, matching the keypoints is performed by comparing the acceptable probability and nearest neighbor location information. Simulation results show that the proposed algorithm achieves more than 90% matching in various types of tissue surface and movement.

AB - In this paper, we proposed a novel algorithm for endoscopic image matching. The algorithm consists of two main components, log-ratio descriptor and probabilistic matching criterion. Log-ratio descriptor is developed by using selected pair of grayscale intensity information that surround the keypoint. The spatial distribution of the pairs follow approximately normal distribution. Then, probabilistic t-test is implemented to produce a distinctive features descriptor. Acceptable probability is calculated based on the probability of t-distribution information. Finally, matching the keypoints is performed by comparing the acceptable probability and nearest neighbor location information. Simulation results show that the proposed algorithm achieves more than 90% matching in various types of tissue surface and movement.

KW - endoscopic image

KW - log ratio descriptor

KW - matching keypoint

UR - http://www.scopus.com/inward/record.url?scp=84907388440&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84907388440&partnerID=8YFLogxK

U2 - 10.1109/SSP.2014.6884606

DO - 10.1109/SSP.2014.6884606

M3 - Conference contribution

SN - 9781479949755

SP - 185

EP - 188

BT - IEEE Workshop on Statistical Signal Processing Proceedings

PB - IEEE Computer Society

ER -