Bangladeshi Indigenous Fish Classification using Convolutional Neural Networks

Dey, Krishno; Hassan, Md. Mustahid; Rana, Md. Masud; Hena, Mst. Hasna

doi:10.1109/icit52682.2021.9491681

Cited by 8 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dey et al 2021 used a FishNet app based on 5-layer CNN for the recognition of eight varieties of indigenous freshwater fish species from Bangladesh. [ 41 ]. An ‘adam’ optimizer was chosen for simulation and three different drop-out rates were applied to the last three fully-connected layers of the CNN.…”

Section: Literature Searchmentioning

confidence: 99%

“…An ‘adam’ optimizer was chosen for simulation and three different drop-out rates were applied to the last three fully-connected layers of the CNN. This method attained a validation accuracy of 99% with a 3.25% validation loss [ 41 ]. Abinaya et al 2021 used the Fish_Pak dataset and segmented fish heads, scales, and body are segmented from those images [ 42 ].…”

Section: Literature Searchmentioning

confidence: 99%

“…Also, fish classification using deep learning requires a lot of training data, which poses a challenge for researchers working alone [ 23 ]. This detailed background search on the fish classification reveals that while marine fish classification is extensively studied by maximum researchers, only a few have investigated freshwater fish [ 17 , 24 – 26 , 35 , 41 , 42 ]. It has been observed that a majority of the studies on automated freshwater fish classification are restricted only to the carp families.…”

Section: Literature Searchmentioning

confidence: 99%

See 2 more Smart Citations

Automated Freshwater Fish Species Classification using Deep CNN

Deka

Laskar

Baklial³

2023

J. Inst. Eng. India Ser. B

View full text Add to dashboard Cite

Freshwater fish is considered a poor man’s protein supplement as they are easily available in lakes, rivers, natural ponds, paddy fields, beels, and fisheries. There are various freshwater fish species that resemble each other, making it difficult to classify them by their external appearance. Manual fish species identification always needs expertise and so, is erroneous. Recently, computer vision along with deep learning plays a significant role in underwater species classification research where the number of species under investigation is always limited to a maximum of eight (8). In this article, we choose deep-learning architectures, AlexNet and Resnet-50, to classify 20 indigenous fresh-water fish species from the North-Eastern parts of India. The two models are fine-tuned for training and validation of the collected fish data. The performance of these networks is evaluated based on overall accuracy, precision, and recall rate. This paper reports the best overall classification accuracy, precision, and recall rate of 100% at a learning rate of 0.001 by the Resnet-50 model on our own dataset and benchmark Fish-Pak dataset. Comprehensive empirical analysis has proved that with an increasing Weight and Bias learning rate, the validation loss incurred by the classifier also increases.

show abstract

Section: Literature Searchmentioning

confidence: 99%

Section: Literature Searchmentioning

confidence: 99%