Recognition of plants using a stochastic L-system model

Ashok K Samal, Brian Peterson, David J. Holliday

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

Recognition of natural shapes like leaves, plants, and trees, has proven to be a challenging problem in computer vision. The members of a class of natural objects are not identical to each other. They are similar, have similar features, but are not exactly the same. Most existing techniques have not succeeded in effectively recognizing these objects. One of the main reasons is that the models used to represent them are inadequate themselves. In this research we use a fractal model, which has been very effective in modeling natural shapes, to represent and then guide the recognition of a class of natural objects, namely plants. Variation in plants is accommodated by using the stochastic L-systems. A learning system is then used to generate a decision tree that can be used for classification. Results show that the approach is successful for a large class of synthetic plants and provides the basis for further research into recognition of natural plants.

Original languageEnglish (US)
Pages (from-to)50-58
Number of pages9
JournalJournal of Electronic Imaging
Volume11
Issue number1
DOIs
StatePublished - Jan 1 2002

Fingerprint

Decision trees
Fractals
Computer vision
Learning systems
computer vision
leaves
learning
fractals

ASJC Scopus subject areas

  • Atomic and Molecular Physics, and Optics
  • Computer Science Applications
  • Electrical and Electronic Engineering

Cite this

Recognition of plants using a stochastic L-system model. / Samal, Ashok K; Peterson, Brian; Holliday, David J.

In: Journal of Electronic Imaging, Vol. 11, No. 1, 01.01.2002, p. 50-58.

Research output: Contribution to journalArticle

Samal, Ashok K ; Peterson, Brian ; Holliday, David J. / Recognition of plants using a stochastic L-system model. In: Journal of Electronic Imaging. 2002 ; Vol. 11, No. 1. pp. 50-58.
@article{da53b09b2b04499ea780a77b797282f4,
title = "Recognition of plants using a stochastic L-system model",
abstract = "Recognition of natural shapes like leaves, plants, and trees, has proven to be a challenging problem in computer vision. The members of a class of natural objects are not identical to each other. They are similar, have similar features, but are not exactly the same. Most existing techniques have not succeeded in effectively recognizing these objects. One of the main reasons is that the models used to represent them are inadequate themselves. In this research we use a fractal model, which has been very effective in modeling natural shapes, to represent and then guide the recognition of a class of natural objects, namely plants. Variation in plants is accommodated by using the stochastic L-systems. A learning system is then used to generate a decision tree that can be used for classification. Results show that the approach is successful for a large class of synthetic plants and provides the basis for further research into recognition of natural plants.",
author = "Samal, {Ashok K} and Brian Peterson and Holliday, {David J.}",
year = "2002",
month = "1",
day = "1",
doi = "10.1117/1.1426081",
language = "English (US)",
volume = "11",
pages = "50--58",
journal = "Journal of Electronic Imaging",
issn = "1017-9909",
publisher = "SPIE",
number = "1",

}

TY - JOUR

T1 - Recognition of plants using a stochastic L-system model

AU - Samal, Ashok K

AU - Peterson, Brian

AU - Holliday, David J.

PY - 2002/1/1

Y1 - 2002/1/1

N2 - Recognition of natural shapes like leaves, plants, and trees, has proven to be a challenging problem in computer vision. The members of a class of natural objects are not identical to each other. They are similar, have similar features, but are not exactly the same. Most existing techniques have not succeeded in effectively recognizing these objects. One of the main reasons is that the models used to represent them are inadequate themselves. In this research we use a fractal model, which has been very effective in modeling natural shapes, to represent and then guide the recognition of a class of natural objects, namely plants. Variation in plants is accommodated by using the stochastic L-systems. A learning system is then used to generate a decision tree that can be used for classification. Results show that the approach is successful for a large class of synthetic plants and provides the basis for further research into recognition of natural plants.

AB - Recognition of natural shapes like leaves, plants, and trees, has proven to be a challenging problem in computer vision. The members of a class of natural objects are not identical to each other. They are similar, have similar features, but are not exactly the same. Most existing techniques have not succeeded in effectively recognizing these objects. One of the main reasons is that the models used to represent them are inadequate themselves. In this research we use a fractal model, which has been very effective in modeling natural shapes, to represent and then guide the recognition of a class of natural objects, namely plants. Variation in plants is accommodated by using the stochastic L-systems. A learning system is then used to generate a decision tree that can be used for classification. Results show that the approach is successful for a large class of synthetic plants and provides the basis for further research into recognition of natural plants.

UR - http://www.scopus.com/inward/record.url?scp=0036205427&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036205427&partnerID=8YFLogxK

U2 - 10.1117/1.1426081

DO - 10.1117/1.1426081

M3 - Article

VL - 11

SP - 50

EP - 58

JO - Journal of Electronic Imaging

JF - Journal of Electronic Imaging

SN - 1017-9909

IS - 1

ER -