Automatic Fish Species Classification Using Deep Convolutional Neural Networks (original) (raw)

Aquarium Family Fish Species Identification System Using Deep Neural Networks

Advances in Intelligent Systems and Computing, 2018

In this paper, a system for aquarium family fish species identification is proposed. It identifies eight family fish species along with 191 sub-species. The proposed system is built using deep convolutional neural networks (CNN). It consists of four layers, two convolutional and two fully connected layers. A comparative result is presented against other CNN architectures such as AlexNet and VggNet according to four parameters (number of convolution and fully connected layers, the number of epochs in training phase to achieve 100% accuracy, validation accuracy, and testing accuracy). Through the paper, it is proven that the proposed system has competitive results against the other architectures. It achieved 85.59% testing accuracy while AlexNet achieves 85.41% over untrained benchmark dataset. Moreover, the proposed system has less trained images, less memory, less computational complexity in training, validation, and testing phases.

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.

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 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.

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.

Fish species recognition using convolutional neural network / Tan Ying Ying

2018

Fish Recognition using machine learning is one of the significant breakthroughs that could be achieved by marine researchers and marine scientists. With the advancement of the machine learning in marine field, some of the problems that perplexed researchers can be solved especially in data collection. Application of machine learning to marine field is still immature, many aspects still need to be improved. Differentiating between two fish species with similar appearance is relatively challenging. On top of that, the angle of fish in the images and the background of the images can cause confusion to the recognition system. Therefore, it is quite challenging to build a fish recognition system. This study focuses on designing a fish recognition system by using Convolutional Neural Network (CNN). The proposed method employs Network-in-Network (NIN) model for fish recognition. NIN model using Multilayer Perceptron (Mlpconv) instead of linear filter and apply Global Average Pooling (GAP) ...

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 Detection Application (FiSDA) in Leyte Gulf Using Convolutional Neural Network

Proceedings of Engineering and Technology Innovation, 2021

This study presents an application that employs a machine-learning algorithm to identify fish species found in Leyte Gulf. It aims to help students and marine scientists with their identification and data collection. The application supports 467 fish species in which 6,918 fish images are used for training, validating, and testing the generated model. The model is trained for a total of 4,000 epochs. Using convolutional neural network (CNN) algorithm, the best model during training is observed at epoch 3,661 with an accuracy rate of 96.49% and a loss value of 0.1359. It obtains 82.81% with a loss value of 1.868 during validation and 80.58% precision during testing. The result shows that the model performs well in predicting Malatindok and Sapsap species, after obtaining the highest precision of 100%. However, Hangit is sometimes misclassified by the model after attaining 55% accuracy rate from the testing results because of its feature similarity to other species.

DEEP CONVOLUTIONAL NETWORKS FOR UNDERWATER FISH LOCALIZATION AND SPECIES CLASSIFICATION

IAEME PUBLICATON, 2020

Live fish recognition is a difficult multi-class order task in the open sea. We propose a technique to perceive fish in an unlimited common habitat.In the proposed technique, VGG-16 with deep fish architecture is used to enhance the feature extraction what's more, to improve the exactness of the result.The proposed approach comprises of two fundamental stages; namely Fish Localization phase and Fish classification phase.The technique first detect the fish from the image by extracting feature map using VGG16 network. DeepFish architectureis used to categorize the Fish.Then, the proposed approach uses support vector machine and random forest classifier to differentiate between fish species. Experimental results obtained show that VGG16 with deepfish architecture using support vector machine attains a better accuracy of 99.47%.

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.