Cargando…
Recognition of Occluded Goods under Prior Inference Based on Generative Adversarial Network
Aiming at the recognition of intelligent retail dynamic visual container goods, two problems that lead to low recognition accuracy must be addressed; one is the lack of goods features caused by the occlusion of the hand, and the other is the high similarity of goods. Therefore, this study proposes a...
Autores principales: | , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10058100/ https://www.ncbi.nlm.nih.gov/pubmed/36992064 http://dx.doi.org/10.3390/s23063355 |
_version_ | 1785016536177573888 |
---|---|
author | Cao, Mingxuan Xie, Kai Liu, Feng Li, Bohao Wen, Chang He, Jianbiao Zhang, Wei |
author_facet | Cao, Mingxuan Xie, Kai Liu, Feng Li, Bohao Wen, Chang He, Jianbiao Zhang, Wei |
author_sort | Cao, Mingxuan |
collection | PubMed |
description | Aiming at the recognition of intelligent retail dynamic visual container goods, two problems that lead to low recognition accuracy must be addressed; one is the lack of goods features caused by the occlusion of the hand, and the other is the high similarity of goods. Therefore, this study proposes an approach for occluding goods recognition based on a generative adversarial network combined with prior inference to address the two abovementioned problems. With DarkNet53 as the backbone network, semantic segmentation is used to locate the occluded part in the feature extraction network, and simultaneously, the YOLOX decoupling head is used to obtain the detection frame. Subsequently, a generative adversarial network under prior inference is used to restore and expand the features of the occluded parts, and a multi-scale spatial attention and effective channel attention weighted attention mechanism module is proposed to select fine-grained features of goods. Finally, a metric learning method based on von Mises–Fisher distribution is proposed to increase the class spacing of features to achieve the effect of feature distinction, whilst the distinguished features are utilized to recognize goods at a fine-grained level. The experimental data used in this study were all obtained from the self-made smart retail container dataset, which contains a total of 12 types of goods used for recognition and includes four couples of similar goods. Experimental results reveal that the peak signal-to-noise ratio and structural similarity under improved prior inference are 0.7743 and 0.0183 higher than those of the other models, respectively. Compared with other optimal models, mAP improves the recognition accuracy by 1.2% and the recognition accuracy by 2.82%. This study solves two problems: one is the occlusion caused by hands, and the other is the high similarity of goods, thus meeting the requirements of commodity recognition accuracy in the field of intelligent retail and exhibiting good application prospects. |
format | Online Article Text |
id | pubmed-10058100 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-100581002023-03-30 Recognition of Occluded Goods under Prior Inference Based on Generative Adversarial Network Cao, Mingxuan Xie, Kai Liu, Feng Li, Bohao Wen, Chang He, Jianbiao Zhang, Wei Sensors (Basel) Article Aiming at the recognition of intelligent retail dynamic visual container goods, two problems that lead to low recognition accuracy must be addressed; one is the lack of goods features caused by the occlusion of the hand, and the other is the high similarity of goods. Therefore, this study proposes an approach for occluding goods recognition based on a generative adversarial network combined with prior inference to address the two abovementioned problems. With DarkNet53 as the backbone network, semantic segmentation is used to locate the occluded part in the feature extraction network, and simultaneously, the YOLOX decoupling head is used to obtain the detection frame. Subsequently, a generative adversarial network under prior inference is used to restore and expand the features of the occluded parts, and a multi-scale spatial attention and effective channel attention weighted attention mechanism module is proposed to select fine-grained features of goods. Finally, a metric learning method based on von Mises–Fisher distribution is proposed to increase the class spacing of features to achieve the effect of feature distinction, whilst the distinguished features are utilized to recognize goods at a fine-grained level. The experimental data used in this study were all obtained from the self-made smart retail container dataset, which contains a total of 12 types of goods used for recognition and includes four couples of similar goods. Experimental results reveal that the peak signal-to-noise ratio and structural similarity under improved prior inference are 0.7743 and 0.0183 higher than those of the other models, respectively. Compared with other optimal models, mAP improves the recognition accuracy by 1.2% and the recognition accuracy by 2.82%. This study solves two problems: one is the occlusion caused by hands, and the other is the high similarity of goods, thus meeting the requirements of commodity recognition accuracy in the field of intelligent retail and exhibiting good application prospects. MDPI 2023-03-22 /pmc/articles/PMC10058100/ /pubmed/36992064 http://dx.doi.org/10.3390/s23063355 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Cao, Mingxuan Xie, Kai Liu, Feng Li, Bohao Wen, Chang He, Jianbiao Zhang, Wei Recognition of Occluded Goods under Prior Inference Based on Generative Adversarial Network |
title | Recognition of Occluded Goods under Prior Inference Based on Generative Adversarial Network |
title_full | Recognition of Occluded Goods under Prior Inference Based on Generative Adversarial Network |
title_fullStr | Recognition of Occluded Goods under Prior Inference Based on Generative Adversarial Network |
title_full_unstemmed | Recognition of Occluded Goods under Prior Inference Based on Generative Adversarial Network |
title_short | Recognition of Occluded Goods under Prior Inference Based on Generative Adversarial Network |
title_sort | recognition of occluded goods under prior inference based on generative adversarial network |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10058100/ https://www.ncbi.nlm.nih.gov/pubmed/36992064 http://dx.doi.org/10.3390/s23063355 |
work_keys_str_mv | AT caomingxuan recognitionofoccludedgoodsunderpriorinferencebasedongenerativeadversarialnetwork AT xiekai recognitionofoccludedgoodsunderpriorinferencebasedongenerativeadversarialnetwork AT liufeng recognitionofoccludedgoodsunderpriorinferencebasedongenerativeadversarialnetwork AT libohao recognitionofoccludedgoodsunderpriorinferencebasedongenerativeadversarialnetwork AT wenchang recognitionofoccludedgoodsunderpriorinferencebasedongenerativeadversarialnetwork AT hejianbiao recognitionofoccludedgoodsunderpriorinferencebasedongenerativeadversarialnetwork AT zhangwei recognitionofoccludedgoodsunderpriorinferencebasedongenerativeadversarialnetwork |