Authors: S.D. Noble And R.B. Brown
Identifier: c0630
Download file: https://library.csbe-scgab.ca/docs/journal/50/c0630.pdf
Published in: CBE Journal » CBE Journal Volume 50 (2008)

Download RAW file:
DOI:
Description: Leaf hape is an important feature used in plant identification. The first stepn automating leaf shape analysis in complex, real-world scenes is toegment individual leaves. Leaves are often occluded and overlapped,. and the similar colour and texture characteristics of the leaves. complicate the task of separating them. A segmentation approach based in simple edge detectors operating on narrow-waveband images from an imaging spectrophotometer was developed and tested. Band. selection was done by comparing separability of leaf-leaf, vein, and. leaf-overlap edge regions of multi-plant, images for four species in 115. spectral bands between 400 and 1000 nm. Testing resulted in a mean. segmentation percentage of 64% using a Sobel edge detector operating on an image in a 5 nm wide waveband centred at 719 nm. This result compared favourably with existing research given the relative. simplicity of the segmentation algorithm and complexity of the test. images used.

Keywords: segmentation, hyperspectral imaging, edge detection, band selection.
Résumé:
Mots-clés:
Citation: Noble, S.D. and Brown, R.B. 2008. Spectral band selection and testing of edge-subtraction leaf segmentation. Canadian Biosystems Engineering 50: 2.1-2.8.
Volume: 50
Issue: 2
Pages 2.1 - 2.8
Contributor:
Date: 2008-01-10
Technical field:
Conference name:
Session name:

Other information:
Type:
Format:
Publication type: Journal
Source:
Relation:
Coverage: Canada
Language 1:
Language 2:
Rights:
Notes:
Other files: