Fish classification using deep learning depending on shape and texture (original) (raw)
Related papers
FishResNet: Automatic Fish Classification Approach in Underwater Scenario
SN Computer Science, 2021
Fish species classification in underwater images is an emerging research area for scientists and researchers in the field of image processing. Fish species classification in underwater images is an important task for fish survey i.e. to audit ecological balance, monitoring fish population and preserving endangered species. But the phenomenon of light scattering and absorption in ocean water leads to hazy, dull and low contrast images making fish classification a tedious and tough task. Convolutional Neural Networks (CNNs) can be the solution for fish species classification problem but the scarcity of ample fish images leads to the serious issue of training a neural network from scratch. To overcome the issue of limited dataset the present paper proposes a transfer learning based fish species classification method for underwater images. ResNet-50 network has been used for transfer learning as it reduces the vanishing gradient problem to minimum by using residual blocks and thus improving the accuracies. Training only last few layers of ResNet-50 network with transfer learning increases the classification accuracy despite of scarce dataset. The proposed method has been tested on two datasets comprising of 27, 370 (i.e. large dataset) and 600 images (i.e. small dataset) without any data augmentation. Experimental results depict that the proposed network achieves a validation accuracy of 98.44% for large dataset and 84.92% for smaller dataset. With the performance analysis, it is observed that this transfer learning based approach led to better results by providing high precision, recall and F1score values of 0.94, 0.85 and 0.89, respectively.
Fish Species Classification using Optimized Deep Learning Model
International Journal of Advanced Computer Science and Applications
Classification of fish species in aquatic pictures is a growing field of research for researchers and image processing experts. Classification of fish species in aquatic images is critical for fish analytical purposes, such as ecological auditing balance, observing fish populations, and saving threatened animals. However, ocean water scattering and absorption of light result in dim and low contrast pictures, making fish classification laborious and challenging. This paper presents an efficient scheme of fish classification, which helps the biologist understand varieties of fish and their surroundings. This proposed system used an improved deep learning-based auto encoder decoder method for fish classification. Optimal feature selection is a major issue with deep learning models generally. To solve this problem efficiently, an enhanced grey wolf optimization technique (EGWO) has been introduced in this study. The accuracy of the classification system for aquatic fish species depends on the essential texture features. Accordingly, in this study, the proposed EGWO has selected the most optimal texture features from the features extracted by the auto encoder. Finally, to prove the efficacy of the proposed method, it is compared to existing deep learning models such as AlexNet, Res Net, VGG Net, and CNN. The proposed method is analysed by varying iterations, batches, and fully connected layers. The analysis of performance criteria such as accuracy, sensitivity, specificity, precision, and F1 score reveals that AED-EGWO gives superior performance.
Automated Freshwater Fish Species Classification using Deep CNN
Journal of The Institution of Engineers (India): Series B
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 freshwater fish species from the NorthEastern 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.
Deep convolutional neural network-based system for fish classification
International Journal of Electrical and Computer Engineering (IJECE), 2022
In computer vision, image classification is one of the potential image processing tasks. Nowadays, fish classification is a wide considered issue within the areas of machine learning and image segmentation. Moreover, it has been extended to a variety of domains, such as marketing strategies. This paper presents an effective fish classification method based on convolutional neural networks (CNNs). The experiments were conducted on the new dataset of Bangladesh’s indigenous fish species with three kinds of splitting: 80-20%, 75-25%, and 70-30%. We provide a comprehensive comparison of several popular optimizers of CNN. In total, we perform a comparative analysis of 5 different state-of-the-art gradient descent-based optimizers, namely adaptive delta (AdaDelta), stochastic gradient descent (SGD), adaptive momentum (Adam), adaptive max pooling (Adamax), Root mean square propagation (Rmsprop), for CNN. Overall, the obtained experimental results show that Rmsprop, Adam, Adamax performed w...
Local Freshwater Fish Recognition Using Different CNN Architectures with Transfer Learning
International Journal on Advanced Science, Engineering and Information Technology, 2021
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.
Fish Species Image Classification Using Convolutional Neural Networks
Journal of Student Research
This paper demonstrates the classification of various fish species using different machine learning methods. By incorporating machine learning algorithms, modeling, and training, the project classifies fish species using neural networks with the help of multiple features like length, width, and more. Ultimately, this project attempts to analyze the differences between determining fish species with PyTorch and TensorFlow. Convolutional Neural Networks (CNN) is a powerful algorithm used in image classification problems. Python has various libraries which can be used to build a model for the same purpose; the ultimate goal of this study is to see whether using different libraries will affect the accuracy. I would like to see whether new and more advanced methods can be used to classify large schools of fish rather than only in labs. I developed separate Python codes using PyTorch and TensorFlow individually. Using each code, I obtained results and, in the end, performed a comparative s...
Fish species recognition using transfer learning techniques
2021
Article history Received October 10, 2020 Revised December 5, 2020 Accepted January 6, 2021 Available online July 31, 2021 Marine species recognition is the process of identifying various species that help in population estimation and identifying the endangered types for taking further remedies and actions. The superior performance of deep learning for classification is due to the property of estimating millions of parameters that have to be extracted from many annotated datasets. However, many types of fish species are becoming extinct, which may reduce the number of samples. The unavailability of a large dataset is a significant hurdle for applying a deep neural network that can be overcome using transfer learning techniques. To overcome this problem, we propose a transfer learning technique using a pre-trained model that uses underwater fish images as input and applies a transfer learning technique to detect the fish species using a pre-trained Google Inception-v3 model. We have ...
Automatic Fish Species Classification Using Deep Convolutional Neural Networks
Wireless Personal Communications, 2019
In this paper, we presented an automated system for identification and classification of fish species. It helps the marine biologists to have greater understanding of the fish species and their habitats. The proposed model is based on deep convolutional neural networks. It uses a reduced version of AlexNet model comprises of four convolutional layers and two fully connected layers. A comparison is presented against the other deep learning models such as AlexNet and VGGNet. The four parameters are considered that is number of convolutional layers and number of fully-connected layers, number of iterations to achieve 100% accuracy on training data, batch size and dropout layer. The results show that the proposed and modified AlexNet model with less number of layers has achieved the testing accuracy of 90.48% while the original AlexNet model achieved 86.65% over the untrained benchmark fish dataset. The inclusion of dropout layer has enhanced the overall performance of our proposed model. It contain less training images, less memory and it is also less computational complex.
Fish species classification in unconstrained underwater environments based on deep learning
Limnology and Oceanography: Methods, 2016
Underwater video and digital still cameras are rapidly being adopted by marine scientists and managers as a tool for non-destructively quantifying and measuring the relative abundance, cover and size of marine fauna and flora. Imagery recorded of fish can be time consuming and costly to process and analyze manually. For this reason, there is great interest in automatic classification, counting, and measurement of fish. Unconstrained underwater scenes are highly variable due to changes in light intensity, changes in fish orientation due to movement, a variety of background habitats which sometimes also move, and most importantly similarity in shape and patterns among fish of different species. This poses a great challenge for image/video processing techniques to accurately differentiate between classes or species of fish to perform automatic classification. We present a machine learning approach, which is suitable for solving this challenge. We demonstrate the use of a convolution neural network model in a hierarchical feature combination setup to learn species-dependent visual features of fish that are unique, yet abstract and robust against environmental and intra-and inter-species variability. This approach avoids the need for explicitly extracting features from raw images of the fish using several fragmented image processing techniques. As a result, we achieve a single and generic trained architecture with favorable performance even for sample images of fish species that have not been used in training. Using the LifeCLEF14 and LifeCLEF15 benchmark fish datasets, we have demonstrated results with a correct classification rate of more than 90%.
Fish Species Classification from Underwater Images using Large-Scale Dataset via Deep Learning
Research Square (Research Square), 2022
Many natural science investigations, including fishery assessment, marine environment assessment, and environmental research, depend on the classification of underwater fish species from apprehended images in habitats. But due to noisy captured images, existing models faced lots of issues during recognition of fish species from the underwater images and to solvu such kind of problem, need to develop a high-performance fish recognition model, although it can be challenging due to the chaotic nature of underwater imagery. In directive to train Deep Neural Network (DNN) in precise manner to develop a Fish Species Classification (FSC) model from noisy large-scale underwater captured images, this research article introduces an inimitable deep learning framework called Optimized DNN. The underwater environment is very fascinating and challenging and many research groups are currently working together to unravel the facts of underwater imaging and mapping. The proposed FSC model is use for fish detection based on the segmentation approach and DNN-based identification in complex underwater environments. To simulate and validate the proposed FSC model, publicly available Fish4Knowledge (Fish Detection) benchmark dataset is used and experimental results show that the FSC model performance is far better in terms of Average Precision (AP = 92.26%), Average Recall (AR = 87.45%), Average F-measure (AF = 89.74%) and Average Accuracy (AA = 93.86%). The composite FSC network model increases the usage of distinctive info and the output of distinctive info for the discovered object.