Cargando…

A comparative study of the effectiveness of using popular DNN object detection algorithms for pith detection in cross-sectional images of parawood

The location of pith in a cross-sectional surface of wood can be used to either evaluate its quality or guide the removal of soft wood from the wood stem. There have been many attempts to automate pith detection in images taken by a normal camera. The objective of this study is to comparatively stud...

Descripción completa

Detalles Bibliográficos
Autor principal: Kurdthongmee, Wattanapong
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Elsevier 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7049650/
https://www.ncbi.nlm.nih.gov/pubmed/32140596
http://dx.doi.org/10.1016/j.heliyon.2020.e03480
_version_ 1783502482664587264
author Kurdthongmee, Wattanapong
author_facet Kurdthongmee, Wattanapong
author_sort Kurdthongmee, Wattanapong
collection PubMed
description The location of pith in a cross-sectional surface of wood can be used to either evaluate its quality or guide the removal of soft wood from the wood stem. There have been many attempts to automate pith detection in images taken by a normal camera. The objective of this study is to comparatively study the effectiveness of two popular deep neural network (DNN) object detection algorithms for parawood pith detection in cross-sectional wood images. In the experiment, a database of 345 cross-sectional images of parawood, taken by a normal camera within a sawmill environment, was quadrupled in size via image augmentation. The images were then manually annotated to label the pith regions. The dataset was used to train two DNN object detection algorithms, an SSD (single shot detector) MobileNet and you-only-look-once (YOLO), via transfer learning. The inference results, utilizing pretrained models obtained by minimizing a loss function in both algorithms, were obtained on a separate dataset of 215 images and compared. The detection rate and average location error with respect to the ground truth were used to evaluate the effectiveness of detection. Additionally, the average distance error results were compared with the results of a state-of-the-art non-DNN algorithm. SSD MobileNet obtained the best detection rate of 87.7% with a ratio of training to test data of 80:20 and 152,000 training iterations. The average distance error of SSD MobileNet is comparable to that of YOLO and six times better than that of the non-DNN algorithm. Hence, SSD MobileNet is an effective approach to automating parawood pith detection in cross-sectional images.
format Online
Article
Text
id pubmed-7049650
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher Elsevier
record_format MEDLINE/PubMed
spelling pubmed-70496502020-03-05 A comparative study of the effectiveness of using popular DNN object detection algorithms for pith detection in cross-sectional images of parawood Kurdthongmee, Wattanapong Heliyon Article The location of pith in a cross-sectional surface of wood can be used to either evaluate its quality or guide the removal of soft wood from the wood stem. There have been many attempts to automate pith detection in images taken by a normal camera. The objective of this study is to comparatively study the effectiveness of two popular deep neural network (DNN) object detection algorithms for parawood pith detection in cross-sectional wood images. In the experiment, a database of 345 cross-sectional images of parawood, taken by a normal camera within a sawmill environment, was quadrupled in size via image augmentation. The images were then manually annotated to label the pith regions. The dataset was used to train two DNN object detection algorithms, an SSD (single shot detector) MobileNet and you-only-look-once (YOLO), via transfer learning. The inference results, utilizing pretrained models obtained by minimizing a loss function in both algorithms, were obtained on a separate dataset of 215 images and compared. The detection rate and average location error with respect to the ground truth were used to evaluate the effectiveness of detection. Additionally, the average distance error results were compared with the results of a state-of-the-art non-DNN algorithm. SSD MobileNet obtained the best detection rate of 87.7% with a ratio of training to test data of 80:20 and 152,000 training iterations. The average distance error of SSD MobileNet is comparable to that of YOLO and six times better than that of the non-DNN algorithm. Hence, SSD MobileNet is an effective approach to automating parawood pith detection in cross-sectional images. Elsevier 2020-02-28 /pmc/articles/PMC7049650/ /pubmed/32140596 http://dx.doi.org/10.1016/j.heliyon.2020.e03480 Text en © 2020 The Author(s) http://creativecommons.org/licenses/by-nc-nd/4.0/ This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
spellingShingle Article
Kurdthongmee, Wattanapong
A comparative study of the effectiveness of using popular DNN object detection algorithms for pith detection in cross-sectional images of parawood
title A comparative study of the effectiveness of using popular DNN object detection algorithms for pith detection in cross-sectional images of parawood
title_full A comparative study of the effectiveness of using popular DNN object detection algorithms for pith detection in cross-sectional images of parawood
title_fullStr A comparative study of the effectiveness of using popular DNN object detection algorithms for pith detection in cross-sectional images of parawood
title_full_unstemmed A comparative study of the effectiveness of using popular DNN object detection algorithms for pith detection in cross-sectional images of parawood
title_short A comparative study of the effectiveness of using popular DNN object detection algorithms for pith detection in cross-sectional images of parawood
title_sort comparative study of the effectiveness of using popular dnn object detection algorithms for pith detection in cross-sectional images of parawood
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7049650/
https://www.ncbi.nlm.nih.gov/pubmed/32140596
http://dx.doi.org/10.1016/j.heliyon.2020.e03480
work_keys_str_mv AT kurdthongmeewattanapong acomparativestudyoftheeffectivenessofusingpopulardnnobjectdetectionalgorithmsforpithdetectionincrosssectionalimagesofparawood
AT kurdthongmeewattanapong comparativestudyoftheeffectivenessofusingpopulardnnobjectdetectionalgorithmsforpithdetectionincrosssectionalimagesofparawood