Developing a Classification CNN Model to Classify Different Types of Fish

Ahmed, Farhan; Basak, Bijoy; Chakraborty, Simonta; Karmokar, Tumpa; Reza, Ahmed Wasif; Imam, Omar Tawhid; Arefin, Mohammad Shamsul

doi:10.1007/978-3-031-19958-5_50

Cited by 9 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed CNN automatically extracts key features from both the spatial (RGB images) and the spectral channel (curves of spectral signatures) independently, then concatenates these relevant features into a single feature vector that is used as an input to the classification stage, which is shown in Figure 6 [40]. Note that each input is evaluated independently and in combination, i.e., by using the spatial and spectral channels [41][42][43].…”

Section: Convolutional Neural Network (Cnn)mentioning

confidence: 99%

“…After feature extraction, a fully connected network with a softmax layer was used to classify the images. Finally, we trained the network, considering the following hyperparameters: 4000 epochs, batch size = 32, 50 epochs for early stopping to avoid overfitting, considering 33% of the training data for validation, and Stochastic Gradient Descent (SGD) algorithm (learning rate = 0.05) [41][42][43]. Thus, the CNN network will evaluate and stop its training in a maximum of 4000 epochs if the validation error does not decrease in 50 consecutive epochs to avoid overfitting.…”

Section: Convolutional Neural Network (Cnn)mentioning

confidence: 99%

See 1 more Smart Citation

A Spatial-Spectral Classification Method Based on Deep Learning for Controlling Pelagic Fish Landings in Chile

Pezoa,

Ramírez,

Godoy

et al. 2023

Sensors

View full text Add to dashboard Cite

Fishing has provided mankind with a protein-rich source of food and labor, allowing for the development of an important industry, which has led to the overexploitation of most targeted fish species. The sustainable management of these natural resources requires effective control of fish landings and, therefore, an accurate calculation of fishing quotas. This work proposes a deep learning-based spatial-spectral method to classify five pelagic species of interest for the Chilean fishing industry, including the targeted Engraulis ringens, Merluccius gayi, and Strangomera bentincki and non-targeted Normanichthtys crockeri and Stromateus stellatus fish species. This proof-of-concept method is composed of two channels of a convolutional neural network (CNN) architecture that processes the Red–Green–Blue (RGB) images and the visible and near-infrared (VIS-NIR) reflectance spectra of each species. The classification results of the CNN model achieved over 94% in all performance metrics, outperforming other state-of-the-art techniques. These results support the potential use of the proposed method to automatically monitor fish landings and, therefore, ensure compliance with the established fishing quotas.

show abstract