An Automated Framework Based on Deep Learning for Shark Recognition
The recent progress in deep learning has given rise to a non-invasive and effective approach for animal biometrics. These modern techniques allow researchers to track animal individuals on a large-scale image database. Typical approaches are suited to a closed-set recognition problem, which is to id...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-07-01
|
| Series: | Journal of Marine Science and Engineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-1312/10/7/942 |
| _version_ | 1827618885569871872 |
|---|---|
| author | Nhat Anh Le Jucheol Moon Christopher G. Lowe Hyun-Il Kim Sang-Il Choi |
| author_facet | Nhat Anh Le Jucheol Moon Christopher G. Lowe Hyun-Il Kim Sang-Il Choi |
| author_sort | Nhat Anh Le |
| collection | DOAJ |
| description | The recent progress in deep learning has given rise to a non-invasive and effective approach for animal biometrics. These modern techniques allow researchers to track animal individuals on a large-scale image database. Typical approaches are suited to a closed-set recognition problem, which is to identify images of known objects only. However, such approaches are not scalable because they mis-classify images of unknown objects. To recognize the images of unknown objects as ‘unknown’, a framework should be able to deal with the open set recognition scenario. This paper proposes a fully automatic, vision-based identification framework capable of recognizing shark individuals including those that are unknown. The framework first detects and extracts the shark from the original image. After that, we develop a deep network to transform the extracted image to an embedding vector in latent space. The proposed network consists of the Visual Geometry Group-UNet (VGG-UNet) and a modified Visual Geometry Group-16 (VGG-16) network. The VGG-UNet is utilized to detect shark bodies, and the modified VGG-16 is used to learn embeddings of shark individuals. For the recognition task, our framework learns a decision boundary using a one-class support vector machine (OSVM) for each shark included in the training phase using a few embedding vectors belonging to them, then it determines whether a new shark image is recognized as belonging to a known shark individual. Our proposed network can recognize shark individuals with high accuracy and can effectively deal with the open set recognition problem with shark images. |
| first_indexed | 2024-03-09T10:16:38Z |
| format | Article |
| id | doaj.art-b2d9e8124ea447bc98728a44af9426ea |
| institution | Directory Open Access Journal |
| issn | 2077-1312 |
| language | English |
| last_indexed | 2024-03-09T10:16:38Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Marine Science and Engineering |
| spelling | doaj.art-b2d9e8124ea447bc98728a44af9426ea2023-12-01T22:19:30ZengMDPI AGJournal of Marine Science and Engineering2077-13122022-07-0110794210.3390/jmse10070942An Automated Framework Based on Deep Learning for Shark RecognitionNhat Anh Le0Jucheol Moon1Christopher G. Lowe2Hyun-Il Kim3Sang-Il Choi4Department of Computer Engineering and Computer Science, California State University, Long Beach, CA 90840, USADepartment of Computer Engineering and Computer Science, California State University, Long Beach, CA 90840, USADepartment of Biological Sciences, California State University, Long Beach, CA 90840, USADepartment of Computer Science and Engineering, Dankook University, Yongin 16890, KoreaDepartment of Computer Science and Engineering, Dankook University, Yongin 16890, KoreaThe recent progress in deep learning has given rise to a non-invasive and effective approach for animal biometrics. These modern techniques allow researchers to track animal individuals on a large-scale image database. Typical approaches are suited to a closed-set recognition problem, which is to identify images of known objects only. However, such approaches are not scalable because they mis-classify images of unknown objects. To recognize the images of unknown objects as ‘unknown’, a framework should be able to deal with the open set recognition scenario. This paper proposes a fully automatic, vision-based identification framework capable of recognizing shark individuals including those that are unknown. The framework first detects and extracts the shark from the original image. After that, we develop a deep network to transform the extracted image to an embedding vector in latent space. The proposed network consists of the Visual Geometry Group-UNet (VGG-UNet) and a modified Visual Geometry Group-16 (VGG-16) network. The VGG-UNet is utilized to detect shark bodies, and the modified VGG-16 is used to learn embeddings of shark individuals. For the recognition task, our framework learns a decision boundary using a one-class support vector machine (OSVM) for each shark included in the training phase using a few embedding vectors belonging to them, then it determines whether a new shark image is recognized as belonging to a known shark individual. Our proposed network can recognize shark individuals with high accuracy and can effectively deal with the open set recognition problem with shark images.https://www.mdpi.com/2077-1312/10/7/942shark recognitiondeep learningOSVMfew-shot learningVGG-UNetVGG-16 |
| spellingShingle | Nhat Anh Le Jucheol Moon Christopher G. Lowe Hyun-Il Kim Sang-Il Choi An Automated Framework Based on Deep Learning for Shark Recognition Journal of Marine Science and Engineering shark recognition deep learning OSVM few-shot learning VGG-UNet VGG-16 |
| title | An Automated Framework Based on Deep Learning for Shark Recognition |
| title_full | An Automated Framework Based on Deep Learning for Shark Recognition |
| title_fullStr | An Automated Framework Based on Deep Learning for Shark Recognition |
| title_full_unstemmed | An Automated Framework Based on Deep Learning for Shark Recognition |
| title_short | An Automated Framework Based on Deep Learning for Shark Recognition |
| title_sort | automated framework based on deep learning for shark recognition |
| topic | shark recognition deep learning OSVM few-shot learning VGG-UNet VGG-16 |
| url | https://www.mdpi.com/2077-1312/10/7/942 |
| work_keys_str_mv | AT nhatanhle anautomatedframeworkbasedondeeplearningforsharkrecognition AT jucheolmoon anautomatedframeworkbasedondeeplearningforsharkrecognition AT christopherglowe anautomatedframeworkbasedondeeplearningforsharkrecognition AT hyunilkim anautomatedframeworkbasedondeeplearningforsharkrecognition AT sangilchoi anautomatedframeworkbasedondeeplearningforsharkrecognition AT nhatanhle automatedframeworkbasedondeeplearningforsharkrecognition AT jucheolmoon automatedframeworkbasedondeeplearningforsharkrecognition AT christopherglowe automatedframeworkbasedondeeplearningforsharkrecognition AT hyunilkim automatedframeworkbasedondeeplearningforsharkrecognition AT sangilchoi automatedframeworkbasedondeeplearningforsharkrecognition |