Cite Article

Local Freshwater Fish Recognition Using Different CNN Architectures with Transfer Learning

Choose citation format

BibTeX

@article{IJASEIT14134,
   author = {Anup Majumder and Aditya Rajbongshi and Md. Mahbubur Rahman and Al Amin Biswas},
   title = {Local Freshwater Fish Recognition Using Different CNN Architectures with Transfer Learning},
   journal = {International Journal on Advanced Science, Engineering and Information Technology},
   volume = {11},
   number = {3},
   year = {2021},
   pages = {1078--1083},
   keywords = {Freshwater local fish; recognition; transfer learning; CNN.},
   abstract = {Bangladesh has its profusion of water resources, but due to environmental issues and some other significant causes, the quantity of water resources is lessening continuously. As a result, many of our local freshwater fishes are being abolished, leading to a lack of knowledge about freshwater fish among the new generation of people in Bangladesh. It is also very difficult to recognize freshwater fish because of their nature, color, shape, and structure. To recognize the local freshwater fish efficiently, transfer learning can be used, one of the significant parts of deep learning that concentrates on storing knowledge gained while solving one problem and employing it to a distinct but related problem. This paper has used six CNN-based architecture with transfer learning, namely DenseNet201, InceptionResnetV2, InceptionV3, ResNet50, ResNet152V2, and Xception. A total of seven freshwater fish image data is used here, which is collected from the various local fish markets of Bangladesh. To check the effectiveness of the working approach, we have calculated the accuracy, precision, Recall, and F1-Score. The approach InceptionResnetV2 and Xception achieved the highest accuracy with 98.81% over the other approach which is a very significant result.},
   issn = {2088-5334},
   publisher = {INSIGHT - Indonesian Society for Knowledge and Human Development},
   url = {http://ijaseit.insightsociety.org/index.php?option=com_content&view=article&id=9&Itemid=1&article_id=14134},
   doi = {10.18517/ijaseit.11.3.14134}
}

EndNote

%A Majumder, Anup
%A Rajbongshi, Aditya
%A Rahman, Md. Mahbubur
%A Biswas, Al Amin
%D 2021
%T Local Freshwater Fish Recognition Using Different CNN Architectures with Transfer Learning
%B 2021
%9 Freshwater local fish; recognition; transfer learning; CNN.
%! Local Freshwater Fish Recognition Using Different CNN Architectures with Transfer Learning
%K Freshwater local fish; recognition; transfer learning; CNN.
%X Bangladesh has its profusion of water resources, but due to environmental issues and some other significant causes, the quantity of water resources is lessening continuously. As a result, many of our local freshwater fishes are being abolished, leading to a lack of knowledge about freshwater fish among the new generation of people in Bangladesh. It is also very difficult to recognize freshwater fish because of their nature, color, shape, and structure. To recognize the local freshwater fish efficiently, transfer learning can be used, one of the significant parts of deep learning that concentrates on storing knowledge gained while solving one problem and employing it to a distinct but related problem. This paper has used six CNN-based architecture with transfer learning, namely DenseNet201, InceptionResnetV2, InceptionV3, ResNet50, ResNet152V2, and Xception. A total of seven freshwater fish image data is used here, which is collected from the various local fish markets of Bangladesh. To check the effectiveness of the working approach, we have calculated the accuracy, precision, Recall, and F1-Score. The approach InceptionResnetV2 and Xception achieved the highest accuracy with 98.81% over the other approach which is a very significant result.
%U http://ijaseit.insightsociety.org/index.php?option=com_content&view=article&id=9&Itemid=1&article_id=14134
%R doi:10.18517/ijaseit.11.3.14134
%J International Journal on Advanced Science, Engineering and Information Technology
%V 11
%N 3
%@ 2088-5334

IEEE

Anup Majumder,Aditya Rajbongshi,Md. Mahbubur Rahman and Al Amin Biswas,"Local Freshwater Fish Recognition Using Different CNN Architectures with Transfer Learning," International Journal on Advanced Science, Engineering and Information Technology, vol. 11, no. 3, pp. 1078-1083, 2021. [Online]. Available: http://dx.doi.org/10.18517/ijaseit.11.3.14134.

RefMan/ProCite (RIS)

TY  - JOUR
AU  - Majumder, Anup
AU  - Rajbongshi, Aditya
AU  - Rahman, Md. Mahbubur
AU  - Biswas, Al Amin
PY  - 2021
TI  - Local Freshwater Fish Recognition Using Different CNN Architectures with Transfer Learning
JF  - International Journal on Advanced Science, Engineering and Information Technology; Vol. 11 (2021) No. 3
Y2  - 2021
SP  - 1078
EP  - 1083
SN  - 2088-5334
PB  - INSIGHT - Indonesian Society for Knowledge and Human Development
KW  - Freshwater local fish; recognition; transfer learning; CNN.
N2  - Bangladesh has its profusion of water resources, but due to environmental issues and some other significant causes, the quantity of water resources is lessening continuously. As a result, many of our local freshwater fishes are being abolished, leading to a lack of knowledge about freshwater fish among the new generation of people in Bangladesh. It is also very difficult to recognize freshwater fish because of their nature, color, shape, and structure. To recognize the local freshwater fish efficiently, transfer learning can be used, one of the significant parts of deep learning that concentrates on storing knowledge gained while solving one problem and employing it to a distinct but related problem. This paper has used six CNN-based architecture with transfer learning, namely DenseNet201, InceptionResnetV2, InceptionV3, ResNet50, ResNet152V2, and Xception. A total of seven freshwater fish image data is used here, which is collected from the various local fish markets of Bangladesh. To check the effectiveness of the working approach, we have calculated the accuracy, precision, Recall, and F1-Score. The approach InceptionResnetV2 and Xception achieved the highest accuracy with 98.81% over the other approach which is a very significant result.
UR  - http://ijaseit.insightsociety.org/index.php?option=com_content&view=article&id=9&Itemid=1&article_id=14134
DO  - 10.18517/ijaseit.11.3.14134

RefWorks

RT Journal Article
ID 14134
A1 Majumder, Anup
A1 Rajbongshi, Aditya
A1 Rahman, Md. Mahbubur
A1 Biswas, Al Amin
T1 Local Freshwater Fish Recognition Using Different CNN Architectures with Transfer Learning
JF International Journal on Advanced Science, Engineering and Information Technology
VO 11
IS 3
YR 2021
SP 1078
OP 1083
SN 2088-5334
PB INSIGHT - Indonesian Society for Knowledge and Human Development
K1 Freshwater local fish; recognition; transfer learning; CNN.
AB Bangladesh has its profusion of water resources, but due to environmental issues and some other significant causes, the quantity of water resources is lessening continuously. As a result, many of our local freshwater fishes are being abolished, leading to a lack of knowledge about freshwater fish among the new generation of people in Bangladesh. It is also very difficult to recognize freshwater fish because of their nature, color, shape, and structure. To recognize the local freshwater fish efficiently, transfer learning can be used, one of the significant parts of deep learning that concentrates on storing knowledge gained while solving one problem and employing it to a distinct but related problem. This paper has used six CNN-based architecture with transfer learning, namely DenseNet201, InceptionResnetV2, InceptionV3, ResNet50, ResNet152V2, and Xception. A total of seven freshwater fish image data is used here, which is collected from the various local fish markets of Bangladesh. To check the effectiveness of the working approach, we have calculated the accuracy, precision, Recall, and F1-Score. The approach InceptionResnetV2 and Xception achieved the highest accuracy with 98.81% over the other approach which is a very significant result.
LK http://ijaseit.insightsociety.org/index.php?option=com_content&view=article&id=9&Itemid=1&article_id=14134
DO  - 10.18517/ijaseit.11.3.14134