Fish Recognition in the Underwater Environment Using an Improved ArcFace Loss for Precision Aquaculture
Accurate fish individual recognition is one of the critical technologies for large-scale fishery farming when trying to achieve accurate, green farming and sustainable development. It is an essential link for aquaculture to move toward automation and intelligence. However, existing fish individual d...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-11-01
|
| Series: | Fishes |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2410-3888/8/12/591 |
| _version_ | 1797381128010596352 |
|---|---|
| author | Liang Liu Junfeng Wu Tao Zheng Haiyan Zhao Han Kong Boyu Qu Hong Yu |
| author_facet | Liang Liu Junfeng Wu Tao Zheng Haiyan Zhao Han Kong Boyu Qu Hong Yu |
| author_sort | Liang Liu |
| collection | DOAJ |
| description | Accurate fish individual recognition is one of the critical technologies for large-scale fishery farming when trying to achieve accurate, green farming and sustainable development. It is an essential link for aquaculture to move toward automation and intelligence. However, existing fish individual data collection methods cannot cope with the interference of light, blur, and pose in the natural underwater environment, which makes the captured fish individual images of poor quality. These low-quality images can cause significant interference with the training of recognition networks. In order to solve the above problems, this paper proposes an underwater fish individual recognition method (FishFace) that combines data quality assessment and loss weighting. First, we introduce the Gem pooing and quality evaluation module, which is based on EfficientNet. This module is an improved fish recognition network that can evaluate the quality of fish images well, and it does not need additional labels; second, we propose a new loss function, FishFace Loss, which will weigh the loss according to the quality of the image so that the model focuses more on recognizable fish images, and less on images that are difficult to recognize. Finally, we collect a dataset for fish individual recognition (WideFish), which contains and annotates 5000 images of 300 fish. The experimental results show that, compared with the state-of-the-art individual recognition methods, Rank1 accuracy is improved by 2.60% and 3.12% on the public dataset DlouFish and the proposed WideFish dataset, respectively. |
| first_indexed | 2024-03-08T20:46:55Z |
| format | Article |
| id | doaj.art-85818bfc9efd4d8abe9ef93b5d08e7cd |
| institution | Directory Open Access Journal |
| issn | 2410-3888 |
| language | English |
| last_indexed | 2024-03-08T20:46:55Z |
| publishDate | 2023-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Fishes |
| spelling | doaj.art-85818bfc9efd4d8abe9ef93b5d08e7cd2023-12-22T14:08:18ZengMDPI AGFishes2410-38882023-11-0181259110.3390/fishes8120591Fish Recognition in the Underwater Environment Using an Improved ArcFace Loss for Precision AquacultureLiang Liu0Junfeng Wu1Tao Zheng2Haiyan Zhao3Han Kong4Boyu Qu5Hong Yu6College of Information Engineering, Dalian Ocean University, Dalian 116023, ChinaCollege of Information Engineering, Dalian Ocean University, Dalian 116023, ChinaCollege of Information Engineering, Dalian Ocean University, Dalian 116023, ChinaCollege of Information Engineering, Dalian Ocean University, Dalian 116023, ChinaCollege of Information Engineering, Dalian Ocean University, Dalian 116023, ChinaCollege of Information Engineering, Dalian Ocean University, Dalian 116023, ChinaCollege of Information Engineering, Dalian Ocean University, Dalian 116023, ChinaAccurate fish individual recognition is one of the critical technologies for large-scale fishery farming when trying to achieve accurate, green farming and sustainable development. It is an essential link for aquaculture to move toward automation and intelligence. However, existing fish individual data collection methods cannot cope with the interference of light, blur, and pose in the natural underwater environment, which makes the captured fish individual images of poor quality. These low-quality images can cause significant interference with the training of recognition networks. In order to solve the above problems, this paper proposes an underwater fish individual recognition method (FishFace) that combines data quality assessment and loss weighting. First, we introduce the Gem pooing and quality evaluation module, which is based on EfficientNet. This module is an improved fish recognition network that can evaluate the quality of fish images well, and it does not need additional labels; second, we propose a new loss function, FishFace Loss, which will weigh the loss according to the quality of the image so that the model focuses more on recognizable fish images, and less on images that are difficult to recognize. Finally, we collect a dataset for fish individual recognition (WideFish), which contains and annotates 5000 images of 300 fish. The experimental results show that, compared with the state-of-the-art individual recognition methods, Rank1 accuracy is improved by 2.60% and 3.12% on the public dataset DlouFish and the proposed WideFish dataset, respectively.https://www.mdpi.com/2410-3888/8/12/591deep learningconvolutional neural networkbiometric recognitionfish individual recognition |
| spellingShingle | Liang Liu Junfeng Wu Tao Zheng Haiyan Zhao Han Kong Boyu Qu Hong Yu Fish Recognition in the Underwater Environment Using an Improved ArcFace Loss for Precision Aquaculture Fishes deep learning convolutional neural network biometric recognition fish individual recognition |
| title | Fish Recognition in the Underwater Environment Using an Improved ArcFace Loss for Precision Aquaculture |
| title_full | Fish Recognition in the Underwater Environment Using an Improved ArcFace Loss for Precision Aquaculture |
| title_fullStr | Fish Recognition in the Underwater Environment Using an Improved ArcFace Loss for Precision Aquaculture |
| title_full_unstemmed | Fish Recognition in the Underwater Environment Using an Improved ArcFace Loss for Precision Aquaculture |
| title_short | Fish Recognition in the Underwater Environment Using an Improved ArcFace Loss for Precision Aquaculture |
| title_sort | fish recognition in the underwater environment using an improved arcface loss for precision aquaculture |
| topic | deep learning convolutional neural network biometric recognition fish individual recognition |
| url | https://www.mdpi.com/2410-3888/8/12/591 |
| work_keys_str_mv | AT liangliu fishrecognitionintheunderwaterenvironmentusinganimprovedarcfacelossforprecisionaquaculture AT junfengwu fishrecognitionintheunderwaterenvironmentusinganimprovedarcfacelossforprecisionaquaculture AT taozheng fishrecognitionintheunderwaterenvironmentusinganimprovedarcfacelossforprecisionaquaculture AT haiyanzhao fishrecognitionintheunderwaterenvironmentusinganimprovedarcfacelossforprecisionaquaculture AT hankong fishrecognitionintheunderwaterenvironmentusinganimprovedarcfacelossforprecisionaquaculture AT boyuqu fishrecognitionintheunderwaterenvironmentusinganimprovedarcfacelossforprecisionaquaculture AT hongyu fishrecognitionintheunderwaterenvironmentusinganimprovedarcfacelossforprecisionaquaculture |