Computer image analyses for detection of maize and soybean kernel quality factors

M. R. Paulsen; W. D. Wigger; J. B. Litchfield; J. B. Sinclair

doi:10.1016/S0021-8634(89)80009-5

Computer image analyses for detection of maize and soybean kernel quality factors

M. R. Paulsen, W. D. Wigger, J. B. Litchfield, J. B. Sinclair

Agricultural and Biological Engineering

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

Abstract

A computer vision system was used to determine the lengths, widths, and projected areas of maize kernels. Measured maize kernel lengths agreed within 0.10 mm of micrometer measurements, and projected areas agreed within 1.8% of calculated areas. An algorithm was developed for detection and classification of fungal-damaged soybeans. The algorithm determined damaged soybeans from non-damaged soybeans with 98% accuracy. Fungi species causing the damage were correctly identified by the algorithm in 66 to 96% of the soybeans tested, depending on which of four species caused the damage.

Original language	English (US)
Pages (from-to)	93-101
Number of pages	9
Journal	Journal of Agricultural Engineering Research
Volume	43
Issue number	C
DOIs	https://doi.org/10.1016/S0021-8634(89)80009-5
State	Published - 1989

ASJC Scopus subject areas

Aquatic Science

Online availability

10.1016/S0021-8634(89)80009-5

Library availability

Discover UIUC Full Text

Cite this

@article{bf592fe5ffe84f5b81823261c77d5574,

title = "Computer image analyses for detection of maize and soybean kernel quality factors",

abstract = "A computer vision system was used to determine the lengths, widths, and projected areas of maize kernels. Measured maize kernel lengths agreed within 0.10 mm of micrometer measurements, and projected areas agreed within 1.8% of calculated areas. An algorithm was developed for detection and classification of fungal-damaged soybeans. The algorithm determined damaged soybeans from non-damaged soybeans with 98% accuracy. Fungi species causing the damage were correctly identified by the algorithm in 66 to 96% of the soybeans tested, depending on which of four species caused the damage.",

author = "Paulsen, {M. R.} and Wigger, {W. D.} and Litchfield, {J. B.} and Sinclair, {J. B.}",

note = "Funding Information: This study was a part of Project No. 55030 of the Agricultural Experiment Station, College of Agriculture, University of Illinois at Urbana-Champaign. The research was supported in part by the Illinois Soybean Program Operating Board and the American Soybean Association. Mr Kevin J. Cavanaugh, laboratory technician, Plant Pathology Dept., University of Illinois at Urbana-Champaign is acknowledged for his work in determining the fungi species causing soybean damage.",

year = "1989",

doi = "10.1016/S0021-8634(89)80009-5",

language = "English (US)",

volume = "43",

pages = "93--101",

journal = "Journal of Agricultural Engineering Research",

issn = "0021-8634",

publisher = "Academic Press",

number = "C",

}

TY - JOUR

T1 - Computer image analyses for detection of maize and soybean kernel quality factors

AU - Paulsen, M. R.

AU - Wigger, W. D.

AU - Litchfield, J. B.

AU - Sinclair, J. B.

N1 - Funding Information: This study was a part of Project No. 55030 of the Agricultural Experiment Station, College of Agriculture, University of Illinois at Urbana-Champaign. The research was supported in part by the Illinois Soybean Program Operating Board and the American Soybean Association. Mr Kevin J. Cavanaugh, laboratory technician, Plant Pathology Dept., University of Illinois at Urbana-Champaign is acknowledged for his work in determining the fungi species causing soybean damage.

PY - 1989

Y1 - 1989

N2 - A computer vision system was used to determine the lengths, widths, and projected areas of maize kernels. Measured maize kernel lengths agreed within 0.10 mm of micrometer measurements, and projected areas agreed within 1.8% of calculated areas. An algorithm was developed for detection and classification of fungal-damaged soybeans. The algorithm determined damaged soybeans from non-damaged soybeans with 98% accuracy. Fungi species causing the damage were correctly identified by the algorithm in 66 to 96% of the soybeans tested, depending on which of four species caused the damage.

AB - A computer vision system was used to determine the lengths, widths, and projected areas of maize kernels. Measured maize kernel lengths agreed within 0.10 mm of micrometer measurements, and projected areas agreed within 1.8% of calculated areas. An algorithm was developed for detection and classification of fungal-damaged soybeans. The algorithm determined damaged soybeans from non-damaged soybeans with 98% accuracy. Fungi species causing the damage were correctly identified by the algorithm in 66 to 96% of the soybeans tested, depending on which of four species caused the damage.

UR - http://www.scopus.com/inward/record.url?scp=38249023283&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=38249023283&partnerID=8YFLogxK

U2 - 10.1016/S0021-8634(89)80009-5

DO - 10.1016/S0021-8634(89)80009-5

M3 - Article

AN - SCOPUS:38249023283

SN - 0021-8634

VL - 43

SP - 93

EP - 101

JO - Journal of Agricultural Engineering Research

JF - Journal of Agricultural Engineering Research

IS - C

ER -

Computer image analyses for detection of maize and soybean kernel quality factors

Abstract

ASJC Scopus subject areas

Online availability

Library availability

Related links

Fingerprint

Cite this