Selection of Norway spruce somatic embryos by computer vision

Jari Hämäläinen, Kari Jokinen

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

Abstract

A computer vision system was developed for the classification of plant somatic embryos. The embryos are in a Petri dish that is transferred with constant speed and they are recognized as they pass a line scan camera. A classification algorithm needs to be installed for every plant species. This paper describes an algorithm for the recognition of Norway spruce (Picea abies) embryos. A short review of conifer micropropagation by somatic embryogenesis is also given. The recognition algorithm is based on features calculated from the boundary of the object. Only part of the boundary corresponding to the developing cotyledons (2 - 15) and the straight sides of the embryo are used for recognition. An index of the length of the cotyledons describes the developmental stage of the embryo. The testing set for classifier performance consisted of 118 embryos and 478 nonembryos. With the classification tolerances chosen 69% of the objects classified as embryos by a human classifier were selected and 31$% rejected. Less than 1% of the nonembryos were classified as embryos. The basic features developed can probably be easily adapted for the recognition of other conifer somatic embryos.
Original languageEnglish
Title of host publicationOptics in Agriculture and Forestry
PublisherInternational Society for Optics and Photonics SPIE
Pages195-205
DOIs
Publication statusPublished - 1992
MoE publication typeA4 Article in a conference publication
EventOptics in Agriculture and Forestry - Boston, United States
Duration: 16 Nov 199216 Nov 1992

Publication series

NameProceedings of SPIE
PublisherSPIE
Volume1836

Conference

ConferenceOptics in Agriculture and Forestry
CountryUnited States
CityBoston
Period16/11/9216/11/92

Fingerprint

computer vision
somatic embryos
embryo (plant)
Picea abies
taxonomy
conifers
cotyledons
micropropagation
somatic embryogenesis
cameras
developmental stages

Cite this

Hämäläinen, J., & Jokinen, K. (1992). Selection of Norway spruce somatic embryos by computer vision. In Optics in Agriculture and Forestry (pp. 195-205). International Society for Optics and Photonics SPIE. Proceedings of SPIE, Vol.. 1836 https://doi.org/10.1117/12.144028
Hämäläinen, Jari ; Jokinen, Kari. / Selection of Norway spruce somatic embryos by computer vision. Optics in Agriculture and Forestry. International Society for Optics and Photonics SPIE, 1992. pp. 195-205 (Proceedings of SPIE, Vol. 1836).
@inproceedings{b213da82181a4b7f9ce540bd508f4d02,
title = "Selection of Norway spruce somatic embryos by computer vision",
abstract = "A computer vision system was developed for the classification of plant somatic embryos. The embryos are in a Petri dish that is transferred with constant speed and they are recognized as they pass a line scan camera. A classification algorithm needs to be installed for every plant species. This paper describes an algorithm for the recognition of Norway spruce (Picea abies) embryos. A short review of conifer micropropagation by somatic embryogenesis is also given. The recognition algorithm is based on features calculated from the boundary of the object. Only part of the boundary corresponding to the developing cotyledons (2 - 15) and the straight sides of the embryo are used for recognition. An index of the length of the cotyledons describes the developmental stage of the embryo. The testing set for classifier performance consisted of 118 embryos and 478 nonembryos. With the classification tolerances chosen 69{\%} of the objects classified as embryos by a human classifier were selected and 31${\%} rejected. Less than 1{\%} of the nonembryos were classified as embryos. The basic features developed can probably be easily adapted for the recognition of other conifer somatic embryos.",
author = "Jari H{\"a}m{\"a}l{\"a}inen and Kari Jokinen",
note = "Project code: S{\"A}H1409",
year = "1992",
doi = "10.1117/12.144028",
language = "English",
series = "Proceedings of SPIE",
publisher = "International Society for Optics and Photonics SPIE",
pages = "195--205",
booktitle = "Optics in Agriculture and Forestry",
address = "United States",

}

Hämäläinen, J & Jokinen, K 1992, Selection of Norway spruce somatic embryos by computer vision. in Optics in Agriculture and Forestry. International Society for Optics and Photonics SPIE, Proceedings of SPIE, vol. 1836, pp. 195-205, Optics in Agriculture and Forestry, Boston, United States, 16/11/92. https://doi.org/10.1117/12.144028

Selection of Norway spruce somatic embryos by computer vision. / Hämäläinen, Jari; Jokinen, Kari.

Optics in Agriculture and Forestry. International Society for Optics and Photonics SPIE, 1992. p. 195-205 (Proceedings of SPIE, Vol. 1836).

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

TY - GEN

T1 - Selection of Norway spruce somatic embryos by computer vision

AU - Hämäläinen, Jari

AU - Jokinen, Kari

N1 - Project code: SÄH1409

PY - 1992

Y1 - 1992

N2 - A computer vision system was developed for the classification of plant somatic embryos. The embryos are in a Petri dish that is transferred with constant speed and they are recognized as they pass a line scan camera. A classification algorithm needs to be installed for every plant species. This paper describes an algorithm for the recognition of Norway spruce (Picea abies) embryos. A short review of conifer micropropagation by somatic embryogenesis is also given. The recognition algorithm is based on features calculated from the boundary of the object. Only part of the boundary corresponding to the developing cotyledons (2 - 15) and the straight sides of the embryo are used for recognition. An index of the length of the cotyledons describes the developmental stage of the embryo. The testing set for classifier performance consisted of 118 embryos and 478 nonembryos. With the classification tolerances chosen 69% of the objects classified as embryos by a human classifier were selected and 31$% rejected. Less than 1% of the nonembryos were classified as embryos. The basic features developed can probably be easily adapted for the recognition of other conifer somatic embryos.

AB - A computer vision system was developed for the classification of plant somatic embryos. The embryos are in a Petri dish that is transferred with constant speed and they are recognized as they pass a line scan camera. A classification algorithm needs to be installed for every plant species. This paper describes an algorithm for the recognition of Norway spruce (Picea abies) embryos. A short review of conifer micropropagation by somatic embryogenesis is also given. The recognition algorithm is based on features calculated from the boundary of the object. Only part of the boundary corresponding to the developing cotyledons (2 - 15) and the straight sides of the embryo are used for recognition. An index of the length of the cotyledons describes the developmental stage of the embryo. The testing set for classifier performance consisted of 118 embryos and 478 nonembryos. With the classification tolerances chosen 69% of the objects classified as embryos by a human classifier were selected and 31$% rejected. Less than 1% of the nonembryos were classified as embryos. The basic features developed can probably be easily adapted for the recognition of other conifer somatic embryos.

U2 - 10.1117/12.144028

DO - 10.1117/12.144028

M3 - Conference article in proceedings

T3 - Proceedings of SPIE

SP - 195

EP - 205

BT - Optics in Agriculture and Forestry

PB - International Society for Optics and Photonics SPIE

ER -

Hämäläinen J, Jokinen K. Selection of Norway spruce somatic embryos by computer vision. In Optics in Agriculture and Forestry. International Society for Optics and Photonics SPIE. 1992. p. 195-205. (Proceedings of SPIE, Vol. 1836). https://doi.org/10.1117/12.144028