Cargando…
Predicting and Visualizing Citrus Color Transformation Using a Deep Mask-Guided Generative Network
Citrus rind color is a good indicator of fruit development, and methods to monitor and predict color transformation therefore help the decisions of crop management practices and harvest schedules. This work presents the complete workflow to predict and visualize citrus color transformation in the or...
Autores principales: | , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
AAAS
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10246884/ https://www.ncbi.nlm.nih.gov/pubmed/37292188 http://dx.doi.org/10.34133/plantphenomics.0057 |
_version_ | 1785055124033372160 |
---|---|
author | Bao, Zehan Li, Weifu Chen, Jun Chen, Hong John, Vijay Xiao, Chi Chen, Yaohui |
author_facet | Bao, Zehan Li, Weifu Chen, Jun Chen, Hong John, Vijay Xiao, Chi Chen, Yaohui |
author_sort | Bao, Zehan |
collection | PubMed |
description | Citrus rind color is a good indicator of fruit development, and methods to monitor and predict color transformation therefore help the decisions of crop management practices and harvest schedules. This work presents the complete workflow to predict and visualize citrus color transformation in the orchard featuring high accuracy and fidelity. A total of 107 sample Navel oranges were observed during the color transformation period, resulting in a dataset containing 7,535 citrus images. A framework is proposed that integrates visual saliency into deep learning, and it consists of a segmentation network, a deep mask-guided generative network, and a loss network with manually designed loss functions. Moreover, the fusion of image features and temporal information enables one single model to predict the rind color at different time intervals, thus effectively shrinking the number of model parameters. The semantic segmentation network of the framework achieves the mean intersection over a union score of 0.9694, and the generative network obtains a peak signal-to-noise ratio of 30.01 and a mean local style loss score of 2.710, which indicate both high quality and similarity of the generated images and are also consistent with human perception. To ease the applications in the real world, the model is ported to an Android-based application for mobile devices. The methods can be readily expanded to other fruit crops with a color transformation period. The dataset and the source code are publicly available at GitHub. |
format | Online Article Text |
id | pubmed-10246884 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | AAAS |
record_format | MEDLINE/PubMed |
spelling | pubmed-102468842023-06-08 Predicting and Visualizing Citrus Color Transformation Using a Deep Mask-Guided Generative Network Bao, Zehan Li, Weifu Chen, Jun Chen, Hong John, Vijay Xiao, Chi Chen, Yaohui Plant Phenomics Research Article Citrus rind color is a good indicator of fruit development, and methods to monitor and predict color transformation therefore help the decisions of crop management practices and harvest schedules. This work presents the complete workflow to predict and visualize citrus color transformation in the orchard featuring high accuracy and fidelity. A total of 107 sample Navel oranges were observed during the color transformation period, resulting in a dataset containing 7,535 citrus images. A framework is proposed that integrates visual saliency into deep learning, and it consists of a segmentation network, a deep mask-guided generative network, and a loss network with manually designed loss functions. Moreover, the fusion of image features and temporal information enables one single model to predict the rind color at different time intervals, thus effectively shrinking the number of model parameters. The semantic segmentation network of the framework achieves the mean intersection over a union score of 0.9694, and the generative network obtains a peak signal-to-noise ratio of 30.01 and a mean local style loss score of 2.710, which indicate both high quality and similarity of the generated images and are also consistent with human perception. To ease the applications in the real world, the model is ported to an Android-based application for mobile devices. The methods can be readily expanded to other fruit crops with a color transformation period. The dataset and the source code are publicly available at GitHub. AAAS 2023-06-07 /pmc/articles/PMC10246884/ /pubmed/37292188 http://dx.doi.org/10.34133/plantphenomics.0057 Text en Copyright © 2023 Zehan Bao et al. https://creativecommons.org/licenses/by/4.0/Exclusive licensee Nanjing Agricultural University. No claim to original U.S. Government Works. Distributed under a Creative Commons Attribution License 4.0 (CC BY 4.0) (https://creativecommons.org/licenses/by/4.0/) . |
spellingShingle | Research Article Bao, Zehan Li, Weifu Chen, Jun Chen, Hong John, Vijay Xiao, Chi Chen, Yaohui Predicting and Visualizing Citrus Color Transformation Using a Deep Mask-Guided Generative Network |
title | Predicting and Visualizing Citrus Color Transformation Using a Deep Mask-Guided Generative Network |
title_full | Predicting and Visualizing Citrus Color Transformation Using a Deep Mask-Guided Generative Network |
title_fullStr | Predicting and Visualizing Citrus Color Transformation Using a Deep Mask-Guided Generative Network |
title_full_unstemmed | Predicting and Visualizing Citrus Color Transformation Using a Deep Mask-Guided Generative Network |
title_short | Predicting and Visualizing Citrus Color Transformation Using a Deep Mask-Guided Generative Network |
title_sort | predicting and visualizing citrus color transformation using a deep mask-guided generative network |
topic | Research Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10246884/ https://www.ncbi.nlm.nih.gov/pubmed/37292188 http://dx.doi.org/10.34133/plantphenomics.0057 |
work_keys_str_mv | AT baozehan predictingandvisualizingcitruscolortransformationusingadeepmaskguidedgenerativenetwork AT liweifu predictingandvisualizingcitruscolortransformationusingadeepmaskguidedgenerativenetwork AT chenjun predictingandvisualizingcitruscolortransformationusingadeepmaskguidedgenerativenetwork AT chenhong predictingandvisualizingcitruscolortransformationusingadeepmaskguidedgenerativenetwork AT johnvijay predictingandvisualizingcitruscolortransformationusingadeepmaskguidedgenerativenetwork AT xiaochi predictingandvisualizingcitruscolortransformationusingadeepmaskguidedgenerativenetwork AT chenyaohui predictingandvisualizingcitruscolortransformationusingadeepmaskguidedgenerativenetwork |