Automated classification of starch granules using supervised pattern recognition of morphological properties

Julie Wilson; Karen Hardy; Richard Allen; Les Copeland; Richard Wrangham; Matthew Collins

doi:10.1016/j.jas.2009.10.024

Automated classification of starch granules using supervised pattern recognition of morphological properties

Julie Wilson, Karen Hardy, Richard Allen, Les Copeland, Richard Wrangham, Matthew Collins

Research output: Contribution to journal › Article › peer-review

Abstract

Image analysis techniques have been used to investigate the likelihood of being able to classify and assign a probability regarding the plant origin of individual starch granules in a collection of granules. Quantifiable variables were used to characterize the granules, and the assignments and probabilities were calculated objectively. We consider the classification of images containing granules of a single species and of mixed species and the possibility of assigning a class to granules of unknown species in an image of a slide obtained from the dental calculus of chimpanzees. (C) 2009 Elsevier Ltd. All rights reserved.

Original language	English
Pages (from-to)	594-604
Number of pages	11
Journal	Journal of archaeological science
Volume	37
Issue number	3
DOIs	https://doi.org/10.1016/j.jas.2009.10.024
Publication status	Published - Mar 2010

Keywords

Starch morphology
Image analysis
Classification
Supervised learning
DENTAL CALCULUS
GRAINS
MAIZE
BP
IDENTIFICATION
AGRICULTURE
ARTIFACTS
PANAMA
DIET

Access to Document

10.1016/j.jas.2009.10.024

http://www.sciencedirect.com/science/article/pii/S0305440309003914

Cite this

@article{f096b301068e4caf9b1bc20e5f5585c3,

title = "Automated classification of starch granules using supervised pattern recognition of morphological properties",

abstract = "Image analysis techniques have been used to investigate the likelihood of being able to classify and assign a probability regarding the plant origin of individual starch granules in a collection of granules. Quantifiable variables were used to characterize the granules, and the assignments and probabilities were calculated objectively. We consider the classification of images containing granules of a single species and of mixed species and the possibility of assigning a class to granules of unknown species in an image of a slide obtained from the dental calculus of chimpanzees. (C) 2009 Elsevier Ltd. All rights reserved.",

keywords = "Starch morphology, Image analysis, Classification, Supervised learning, DENTAL CALCULUS, GRAINS, MAIZE, BP, IDENTIFICATION, AGRICULTURE, ARTIFACTS, PANAMA, DIET",

author = "Julie Wilson and Karen Hardy and Richard Allen and Les Copeland and Richard Wrangham and Matthew Collins",

year = "2010",

month = mar,

doi = "10.1016/j.jas.2009.10.024",

language = "English",

volume = "37",

pages = "594--604",

journal = "Journal of archaeological science",

issn = "0305-4403",

publisher = "Elsevier",

number = "3",

}

TY - JOUR

T1 - Automated classification of starch granules using supervised pattern recognition of morphological properties

AU - Wilson, Julie

AU - Hardy, Karen

AU - Allen, Richard

AU - Copeland, Les

AU - Wrangham, Richard

AU - Collins, Matthew

PY - 2010/3

Y1 - 2010/3

N2 - Image analysis techniques have been used to investigate the likelihood of being able to classify and assign a probability regarding the plant origin of individual starch granules in a collection of granules. Quantifiable variables were used to characterize the granules, and the assignments and probabilities were calculated objectively. We consider the classification of images containing granules of a single species and of mixed species and the possibility of assigning a class to granules of unknown species in an image of a slide obtained from the dental calculus of chimpanzees. (C) 2009 Elsevier Ltd. All rights reserved.

AB - Image analysis techniques have been used to investigate the likelihood of being able to classify and assign a probability regarding the plant origin of individual starch granules in a collection of granules. Quantifiable variables were used to characterize the granules, and the assignments and probabilities were calculated objectively. We consider the classification of images containing granules of a single species and of mixed species and the possibility of assigning a class to granules of unknown species in an image of a slide obtained from the dental calculus of chimpanzees. (C) 2009 Elsevier Ltd. All rights reserved.

KW - Starch morphology

KW - Image analysis

KW - Classification

KW - Supervised learning

KW - DENTAL CALCULUS

KW - GRAINS

KW - MAIZE

KW - BP

KW - IDENTIFICATION

KW - AGRICULTURE

KW - ARTIFACTS

KW - PANAMA

KW - DIET

UR - http://www.scopus.com/inward/record.url?scp=72649096966&partnerID=8YFLogxK

U2 - 10.1016/j.jas.2009.10.024

DO - 10.1016/j.jas.2009.10.024

M3 - Article

SN - 0305-4403

VL - 37

SP - 594

EP - 604

JO - Journal of archaeological science

JF - Journal of archaeological science

IS - 3

ER -

Automated classification of starch granules using supervised pattern recognition of morphological properties

Abstract

Keywords

Access to Document

Other files and links

Automated analysis of crystallisation experiments

Cite this

Automated classification of starch granules using supervised pattern recognition of morphological properties

Abstract

Keywords

Access to Document

Other files and links

Projects

Automated analysis of crystallisation experiments

Cite this