Contour analysis for interpretable leaf shape category discovery
Abstract Background The categorical description of leaf shapes is of paramount importance in ecology, taxonomy and paleobotanical studies. Classification systems proposed by domain experts support these descriptions. Despite the importance of these visual descriptive systems, classifications based o...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2019-10-01
|
Series: | Plant Methods |
Subjects: | |
Online Access: | http://link.springer.com/article/10.1186/s13007-019-0497-6 |
id |
doaj-0f6cc614ac7b423da53dac8b4e25b24e |
---|---|
record_format |
Article |
spelling |
doaj-0f6cc614ac7b423da53dac8b4e25b24e2020-11-25T03:57:23ZengBMCPlant Methods1746-48112019-10-0115111210.1186/s13007-019-0497-6Contour analysis for interpretable leaf shape category discoveryJorge Victorino0Francisco Gómez1Departament of System Engineering, Universidad CentralDepartamento de matemáticas, Universidad Nacional de ColombiaAbstract Background The categorical description of leaf shapes is of paramount importance in ecology, taxonomy and paleobotanical studies. Classification systems proposed by domain experts support these descriptions. Despite the importance of these visual descriptive systems, classifications based on this expert’s knowledge may be ambiguous or limited when representing shapes in unknown scenarios, as expected for biological exploratory domains. This work proposes a novel strategy to automatically discover the shape categories in a set of unlabeled leaves by only using the leaf-shape information. In particular, we overcome the task of discovering shape categories from different plant species for three different biological settings. Results The proposed method may successfully infer the unknown underlying shape categories with an F-score greater than 92%. Conclusions The approach also provided high levels of visual interpretability, an essential requirement in the description of biological objects. This method may support morphological analysis of biological objects in exploratory domains.http://link.springer.com/article/10.1186/s13007-019-0497-6Category discoveryContour analysisInterpretabilityLeaf shapeMorphological description |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Jorge Victorino Francisco Gómez |
spellingShingle |
Jorge Victorino Francisco Gómez Contour analysis for interpretable leaf shape category discovery Plant Methods Category discovery Contour analysis Interpretability Leaf shape Morphological description |
author_facet |
Jorge Victorino Francisco Gómez |
author_sort |
Jorge Victorino |
title |
Contour analysis for interpretable leaf shape category discovery |
title_short |
Contour analysis for interpretable leaf shape category discovery |
title_full |
Contour analysis for interpretable leaf shape category discovery |
title_fullStr |
Contour analysis for interpretable leaf shape category discovery |
title_full_unstemmed |
Contour analysis for interpretable leaf shape category discovery |
title_sort |
contour analysis for interpretable leaf shape category discovery |
publisher |
BMC |
series |
Plant Methods |
issn |
1746-4811 |
publishDate |
2019-10-01 |
description |
Abstract Background The categorical description of leaf shapes is of paramount importance in ecology, taxonomy and paleobotanical studies. Classification systems proposed by domain experts support these descriptions. Despite the importance of these visual descriptive systems, classifications based on this expert’s knowledge may be ambiguous or limited when representing shapes in unknown scenarios, as expected for biological exploratory domains. This work proposes a novel strategy to automatically discover the shape categories in a set of unlabeled leaves by only using the leaf-shape information. In particular, we overcome the task of discovering shape categories from different plant species for three different biological settings. Results The proposed method may successfully infer the unknown underlying shape categories with an F-score greater than 92%. Conclusions The approach also provided high levels of visual interpretability, an essential requirement in the description of biological objects. This method may support morphological analysis of biological objects in exploratory domains. |
topic |
Category discovery Contour analysis Interpretability Leaf shape Morphological description |
url |
http://link.springer.com/article/10.1186/s13007-019-0497-6 |
work_keys_str_mv |
AT jorgevictorino contouranalysisforinterpretableleafshapecategorydiscovery AT franciscogomez contouranalysisforinterpretableleafshapecategorydiscovery |
_version_ |
1724461193225043968 |