A NOVEL RAISIN SEGMENTATION ALGORITHM BASED ON DEEP LEARNING AND MORPHOLOGICAL ANALYSIS
Autor(a) principal: | |
---|---|
Data de Publicação: | 2019 |
Outros Autores: | , , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Engenharia Agrícola |
Texto Completo: | http://old.scielo.br/scielo.php?script=sci_arttext&pid=S0100-69162019000500639 |
Resumo: | ABSTRACT We propose a segmentation algorithm for raisin extraction. The proposed approach consists of the following aspects. Deep learning is used to predict the number of raisins in each connected region, and the shape features such as the roundness, area, X-axis value for the centroid, Y-axis value for the centroid, axis length and perimeter of each region will be used to establish the prediction model. Morphological analysis, based on edge parameters including the polar axis, polar angle and angular velocity, is applied to search for the suitable break points that are useful for identifying the dividing lines between two adjacent raisins. To make our segmentation more accurate, some machine-learning algorithms such as the random forest (RF), support vector machine (SVM) and deep learning (deep neural network, DNN) are applied to predict the number of raisins and to decide whether the raisins need more segmentation. The performance of the three models is compared, and the DNN is the most accurate. |
id |
SBEA-1_be8ab889bba3a68d36962da2f024ccc5 |
---|---|
oai_identifier_str |
oai:scielo:S0100-69162019000500639 |
network_acronym_str |
SBEA-1 |
network_name_str |
Engenharia Agrícola |
repository_id_str |
|
spelling |
A NOVEL RAISIN SEGMENTATION ALGORITHM BASED ON DEEP LEARNING AND MORPHOLOGICAL ANALYSISraisin extractionsegmentation algorithmdeep learningimage analysisfood quality gradingABSTRACT We propose a segmentation algorithm for raisin extraction. The proposed approach consists of the following aspects. Deep learning is used to predict the number of raisins in each connected region, and the shape features such as the roundness, area, X-axis value for the centroid, Y-axis value for the centroid, axis length and perimeter of each region will be used to establish the prediction model. Morphological analysis, based on edge parameters including the polar axis, polar angle and angular velocity, is applied to search for the suitable break points that are useful for identifying the dividing lines between two adjacent raisins. To make our segmentation more accurate, some machine-learning algorithms such as the random forest (RF), support vector machine (SVM) and deep learning (deep neural network, DNN) are applied to predict the number of raisins and to decide whether the raisins need more segmentation. The performance of the three models is compared, and the DNN is the most accurate.Associação Brasileira de Engenharia Agrícola2019-10-01info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersiontext/htmlhttp://old.scielo.br/scielo.php?script=sci_arttext&pid=S0100-69162019000500639Engenharia Agrícola v.39 n.5 2019reponame:Engenharia Agrícolainstname:Associação Brasileira de Engenharia Agrícola (SBEA)instacron:SBEA10.1590/1809-4430-eng.agric.v39n5p639-648/2019info:eu-repo/semantics/openAccessZhao,YunGuindo,Mahamed L.Xu,XingShi,XiangSun,MiaoHe,Yongeng2019-10-29T00:00:00Zoai:scielo:S0100-69162019000500639Revistahttp://www.engenhariaagricola.org.br/ORGhttps://old.scielo.br/oai/scielo-oai.phprevistasbea@sbea.org.br||sbea@sbea.org.br1809-44300100-6916opendoar:2019-10-29T00:00Engenharia Agrícola - Associação Brasileira de Engenharia Agrícola (SBEA)false |
dc.title.none.fl_str_mv |
A NOVEL RAISIN SEGMENTATION ALGORITHM BASED ON DEEP LEARNING AND MORPHOLOGICAL ANALYSIS |
title |
A NOVEL RAISIN SEGMENTATION ALGORITHM BASED ON DEEP LEARNING AND MORPHOLOGICAL ANALYSIS |
spellingShingle |
A NOVEL RAISIN SEGMENTATION ALGORITHM BASED ON DEEP LEARNING AND MORPHOLOGICAL ANALYSIS Zhao,Yun raisin extraction segmentation algorithm deep learning image analysis food quality grading |
title_short |
A NOVEL RAISIN SEGMENTATION ALGORITHM BASED ON DEEP LEARNING AND MORPHOLOGICAL ANALYSIS |
title_full |
A NOVEL RAISIN SEGMENTATION ALGORITHM BASED ON DEEP LEARNING AND MORPHOLOGICAL ANALYSIS |
title_fullStr |
A NOVEL RAISIN SEGMENTATION ALGORITHM BASED ON DEEP LEARNING AND MORPHOLOGICAL ANALYSIS |
title_full_unstemmed |
A NOVEL RAISIN SEGMENTATION ALGORITHM BASED ON DEEP LEARNING AND MORPHOLOGICAL ANALYSIS |
title_sort |
A NOVEL RAISIN SEGMENTATION ALGORITHM BASED ON DEEP LEARNING AND MORPHOLOGICAL ANALYSIS |
author |
Zhao,Yun |
author_facet |
Zhao,Yun Guindo,Mahamed L. Xu,Xing Shi,Xiang Sun,Miao He,Yong |
author_role |
author |
author2 |
Guindo,Mahamed L. Xu,Xing Shi,Xiang Sun,Miao He,Yong |
author2_role |
author author author author author |
dc.contributor.author.fl_str_mv |
Zhao,Yun Guindo,Mahamed L. Xu,Xing Shi,Xiang Sun,Miao He,Yong |
dc.subject.por.fl_str_mv |
raisin extraction segmentation algorithm deep learning image analysis food quality grading |
topic |
raisin extraction segmentation algorithm deep learning image analysis food quality grading |
description |
ABSTRACT We propose a segmentation algorithm for raisin extraction. The proposed approach consists of the following aspects. Deep learning is used to predict the number of raisins in each connected region, and the shape features such as the roundness, area, X-axis value for the centroid, Y-axis value for the centroid, axis length and perimeter of each region will be used to establish the prediction model. Morphological analysis, based on edge parameters including the polar axis, polar angle and angular velocity, is applied to search for the suitable break points that are useful for identifying the dividing lines between two adjacent raisins. To make our segmentation more accurate, some machine-learning algorithms such as the random forest (RF), support vector machine (SVM) and deep learning (deep neural network, DNN) are applied to predict the number of raisins and to decide whether the raisins need more segmentation. The performance of the three models is compared, and the DNN is the most accurate. |
publishDate |
2019 |
dc.date.none.fl_str_mv |
2019-10-01 |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://old.scielo.br/scielo.php?script=sci_arttext&pid=S0100-69162019000500639 |
url |
http://old.scielo.br/scielo.php?script=sci_arttext&pid=S0100-69162019000500639 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
10.1590/1809-4430-eng.agric.v39n5p639-648/2019 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
text/html |
dc.publisher.none.fl_str_mv |
Associação Brasileira de Engenharia Agrícola |
publisher.none.fl_str_mv |
Associação Brasileira de Engenharia Agrícola |
dc.source.none.fl_str_mv |
Engenharia Agrícola v.39 n.5 2019 reponame:Engenharia Agrícola instname:Associação Brasileira de Engenharia Agrícola (SBEA) instacron:SBEA |
instname_str |
Associação Brasileira de Engenharia Agrícola (SBEA) |
instacron_str |
SBEA |
institution |
SBEA |
reponame_str |
Engenharia Agrícola |
collection |
Engenharia Agrícola |
repository.name.fl_str_mv |
Engenharia Agrícola - Associação Brasileira de Engenharia Agrícola (SBEA) |
repository.mail.fl_str_mv |
revistasbea@sbea.org.br||sbea@sbea.org.br |
_version_ |
1752126274450489344 |