1
|
Cao M, Xie K, Liu F, Li B, Wen C, He J, Zhang W. Recognition of Occluded Goods under Prior Inference Based on Generative Adversarial Network. SENSORS (BASEL, SWITZERLAND) 2023; 23:3355. [PMID: 36992064 PMCID: PMC10058100 DOI: 10.3390/s23063355] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 12/23/2022] [Revised: 02/11/2023] [Accepted: 03/21/2023] [Indexed: 06/19/2023]
Abstract
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.
Collapse
Affiliation(s)
- Mingxuan Cao
- School of Electronic and Information, Yangtze University, Jingzhou 434023, China
- National Electrical and Electronic Experimental Teaching Demonstration Center, Yangtze University, Jingzhou 434023, China
| | - Kai Xie
- School of Electronic and Information, Yangtze University, Jingzhou 434023, China
- National Electrical and Electronic Experimental Teaching Demonstration Center, Yangtze University, Jingzhou 434023, China
- Western Research Institute, Yangtze University, Karamay 834000, China
| | - Feng Liu
- School of Electronic and Information, Yangtze University, Jingzhou 434023, China
- National Electrical and Electronic Experimental Teaching Demonstration Center, Yangtze University, Jingzhou 434023, China
| | - Bohao Li
- School of Electronic and Information, Yangtze University, Jingzhou 434023, China
- National Electrical and Electronic Experimental Teaching Demonstration Center, Yangtze University, Jingzhou 434023, China
| | - Chang Wen
- Western Research Institute, Yangtze University, Karamay 834000, China
- School of Computer Science, Yangtze University, Jingzhou 434023, China
| | - Jianbiao He
- School of Computer Science and Engineering, Central South University, Changsha 410083, China
| | - Wei Zhang
- School of Computer Science and Engineering, Central South University, Changsha 410083, China
| |
Collapse
|
2
|
Barhate D, Pathak S, Dubey AK. Hyperparameter-tuned batch-updated stochastic gradient descent: Plant species identification by using hybrid deep learning. ECOL INFORM 2023. [DOI: 10.1016/j.ecoinf.2023.102094] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 04/03/2023]
|
3
|
Balasundaram A, Dilip G, Ashokkumar S, Manickam M, Gurunathan K, Kothandaraman D. Detecting True Medicinal Leaves Among Similar Leaves Using Computer Vision and CNN. NATIONAL ACADEMY SCIENCE LETTERS 2023. [DOI: 10.1007/s40009-023-01210-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/25/2023]
|
4
|
Sharma G, Kumar A, Gour N, Saini AK, Upadhyay A, Kumar A. Cognitive framework and learning paradigms of plant leaf classification using artificial neural network and support vector machine. J EXP THEOR ARTIF IN 2022. [DOI: 10.1080/0952813x.2022.2096698] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/17/2022]
Affiliation(s)
- Gajanand Sharma
- Department of Computer Science & Engineering, JECRC University, Jaipur, India
| | - Ashutosh Kumar
- Department of Computer Science & Engineering, JECRC University, Jaipur, India
| | - Nidhi Gour
- Department of Computer Science & Engineering, JECRC University, Jaipur, India
| | - Ashok Kumar Saini
- Department of Computer Science & Engineering, JECRC University, Jaipur, India
| | - Aditya Upadhyay
- Department of Computer Science & Engineering, JECRC University, Jaipur, India
| | - Ankit Kumar
- Department of Computer Engineering & Application, GLA University, Mathura, India
| |
Collapse
|
5
|
Ganguly S, Bhowal P, Oliva D, Sarkar R. BLeafNet: A Bonferroni mean operator based fusion of CNN models for plant identification using leaf image classification. ECOL INFORM 2022. [DOI: 10.1016/j.ecoinf.2022.101585] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/03/2022]
|
6
|
Chaudhury A, Boudon F, Godin C. 3D Plant Phenotyping: All You Need is Labelled Point Cloud Data. COMPUTER VISION – ECCV 2020 WORKSHOPS 2020:244-260. [DOI: 10.1007/978-3-030-65414-6_18] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 07/19/2023]
|