Stitching algorithms for biological specimen images

Sanjiv K. Bhatia, Ashok K Samal, Vishal Seri, Scott L Gardner

Research output: Contribution to journalArticle

Abstract

In this paper, we address the problem of combining multiple overlapping image sections of biological specimens to obtain a single image containing the entire specimen. This is useful in the digitisation of a large number of biological specimens stored in museum collections and laboratories. In the case of many large specimens, it means that the specimen must be captured in overlapping sections instead of a single image. In this research, we have compared the performance of several known algorithms for this problem. In addition, we have developed several new algorithms based on matching the geometry (width, slope, and curvature) of the specimens at the boundaries. Finally, we compare the performance of a bagging approach that combines the results from multiple stitching algorithms. Our detailed evaluation shows that brightness-based and curvature-based approaches produce the best matches for the images in this domain.

Original languageEnglish (US)
Pages (from-to)1-17
Number of pages17
JournalInternational Journal of Computational Vision and Robotics
Volume2
Issue number1
DOIs
StatePublished - Jan 1 2011

Fingerprint

Analog to digital conversion
Museums
Luminance
Geometry

Keywords

  • biological specimen
  • geometry-based matching
  • image stitching

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Computer Science Applications

Cite this

Stitching algorithms for biological specimen images. / Bhatia, Sanjiv K.; Samal, Ashok K; Seri, Vishal; Gardner, Scott L.

In: International Journal of Computational Vision and Robotics, Vol. 2, No. 1, 01.01.2011, p. 1-17.

Research output: Contribution to journalArticle

@article{3d1dc5aab81746398e9e865121545620,
title = "Stitching algorithms for biological specimen images",
abstract = "In this paper, we address the problem of combining multiple overlapping image sections of biological specimens to obtain a single image containing the entire specimen. This is useful in the digitisation of a large number of biological specimens stored in museum collections and laboratories. In the case of many large specimens, it means that the specimen must be captured in overlapping sections instead of a single image. In this research, we have compared the performance of several known algorithms for this problem. In addition, we have developed several new algorithms based on matching the geometry (width, slope, and curvature) of the specimens at the boundaries. Finally, we compare the performance of a bagging approach that combines the results from multiple stitching algorithms. Our detailed evaluation shows that brightness-based and curvature-based approaches produce the best matches for the images in this domain.",
keywords = "biological specimen, geometry-based matching, image stitching",
author = "Bhatia, {Sanjiv K.} and Samal, {Ashok K} and Vishal Seri and Gardner, {Scott L}",
year = "2011",
month = "1",
day = "1",
doi = "10.1504/IJCVR.2011.039354",
language = "English (US)",
volume = "2",
pages = "1--17",
journal = "International Journal of Computational Vision and Robotics",
issn = "1752-9131",
publisher = "Inderscience Enterprises Ltd",
number = "1",

}

TY - JOUR

T1 - Stitching algorithms for biological specimen images

AU - Bhatia, Sanjiv K.

AU - Samal, Ashok K

AU - Seri, Vishal

AU - Gardner, Scott L

PY - 2011/1/1

Y1 - 2011/1/1

N2 - In this paper, we address the problem of combining multiple overlapping image sections of biological specimens to obtain a single image containing the entire specimen. This is useful in the digitisation of a large number of biological specimens stored in museum collections and laboratories. In the case of many large specimens, it means that the specimen must be captured in overlapping sections instead of a single image. In this research, we have compared the performance of several known algorithms for this problem. In addition, we have developed several new algorithms based on matching the geometry (width, slope, and curvature) of the specimens at the boundaries. Finally, we compare the performance of a bagging approach that combines the results from multiple stitching algorithms. Our detailed evaluation shows that brightness-based and curvature-based approaches produce the best matches for the images in this domain.

AB - In this paper, we address the problem of combining multiple overlapping image sections of biological specimens to obtain a single image containing the entire specimen. This is useful in the digitisation of a large number of biological specimens stored in museum collections and laboratories. In the case of many large specimens, it means that the specimen must be captured in overlapping sections instead of a single image. In this research, we have compared the performance of several known algorithms for this problem. In addition, we have developed several new algorithms based on matching the geometry (width, slope, and curvature) of the specimens at the boundaries. Finally, we compare the performance of a bagging approach that combines the results from multiple stitching algorithms. Our detailed evaluation shows that brightness-based and curvature-based approaches produce the best matches for the images in this domain.

KW - biological specimen

KW - geometry-based matching

KW - image stitching

UR - http://www.scopus.com/inward/record.url?scp=84948647767&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84948647767&partnerID=8YFLogxK

U2 - 10.1504/IJCVR.2011.039354

DO - 10.1504/IJCVR.2011.039354

M3 - Article

AN - SCOPUS:84948647767

VL - 2

SP - 1

EP - 17

JO - International Journal of Computational Vision and Robotics

JF - International Journal of Computational Vision and Robotics

SN - 1752-9131

IS - 1

ER -