A Large-Scale Dataset for Fish Segmentation and Classification

Ulucan, Oguzhan; Karakaya, Diclehan; Türkan, Mehmet

doi:10.1109/asyu50717.2020.9259867

Cited by 44 publications

(25 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The research method consists of 6 stages, namely: First, Literature study to find literature and references as a reference for conducting research both from books, journals, proceedings, and others. Furthermore, data collection was carried out by searching for the dataset to be used in this study, the data used were sourced from Kaggle.Com [16]. After the dataset in the form of an image has been collected, before processing, the data must then be cleaned first at the image pre-processing stage, at this stage the background is removed to black then adjusts the overall dimensions of the image to 1024 × 768 pixels, this is intended so that At the time of extracting the value in the image, only the value of the fish object is extracted, while the purpose of adjusting the dimensions of the image is to ensure the extraction value is taken from the same number of pixels.…”

Section: Methodsmentioning

confidence: 99%

Classification of Fish Species with Image Data Using K-Nearest Neighbor

Kaharuddin

Sholeha

2021

IJCIS

View full text Add to dashboard Cite

Abstract— Classification is a technique that many of us encounter in everyday life, classification science is also growing and being applied to various types of data and cases in everyday life, in computer science classification has been developed to facilitate human work, one example of its application is to classify fish species in the world, the number of fish species in the world is very much so that there are still many people who are sometimes confused to distinguish them, therefore in this study a study will be conducted to classify fish species using the K-Nearest Neighbor Method. 4 types of fish, all data totaling 160 data. The purpose of this study was to test the K-Nearest Neighbor method for classifying fish species based on color, texture, and shape features. Based on the test results, the accuracy value of the truth is obtained using the value of K = 7 with a percentage of the truth of 77.50%, the second-highest accuracy value is the value of K = 10, namely 76.88%. Based on the results of this study, it can be concluded that the K-Nearest Neighbor method has a good enough ability to classify, but it can be done by adding variables or adding more amount of data, and using other types of fish.

show abstract

Section: Methodsmentioning

confidence: 99%

Classification of Fish Species with Image Data Using K-Nearest Neighbor

Kaharuddin

Sholeha

2021

IJCIS

View full text Add to dashboard Cite

show abstract

“…This was the first dataset employed to train the model using the proposed method. Animal models were introduced by Choi et al [29]. The dataset consisted of 16130 high-quality 512 × 512 images.…”

Section: ) Animal Facesmentioning

confidence: 99%

KeepNMax: Keep N Maximum of Epoch-Channel Ensemble Method for Deep Learning Models

et al. 2023

View full text Add to dashboard Cite

Computer vision (CV) application is becoming a crucial factor for the growth of developed economies in the world. The widespread use of CV applications has created a growing demand for accurate models. Therefore, the subfields of CV focus on improving existing models and developing new methods and algorithms to meet the demands of different sectors. Simultaneously, research on ensemble learning provides effective tools for increasing the accuracies of the models. Nevertheless, there is a significant gap in research using data representation and model features. This led us to develop KeepNMax-an ensemble of image channels and epochs using the top N maximum prediction probabilities at the final step. Using KeepNMax, the ensemble error was reduced and increased the amount of data knowledge of the ensemble model. Nine datasets were trained. As long as each dataset had three channels, the images were divided into three different channels and trained them separately using the same model architecture. In addition, the datasets were trained without dividing them into different channels using the same model architecture. After completing the training, some epochs of the training were ensembled to the best epoch in the training. In addition, two different model architectures were used to check the model dependency of the proposed method and achieved remarkable results in both cases. This method was proposed for deep-learning classification models. Despite its simplicity, proposed method improved the results of the CNN and ConvMixer models for the datasets used. Classic training, bootstrap aggregation, and random split methods were used as the baseline methods. For most datasets, significant results were obtained using KeepNMax. The success of the method was explained by the unique true prediction (UTP) scope of each model. By ensembling the models, the prediction scope of the model was enlarged, allowing it to represent broader knowledge about datasets than a simple model. INDEX TERMSEpoch ensemble, channel ensemble, top N prediction probabilities ensemble.

show abstract

“…The author confirms that the ethical policies of the journal, as noted on the journal's author guidelines page, have been adhered to. No ethical approval was required as the data used in the experiment was obtained from published literature [82].…”

Section: Ethics Statementmentioning

confidence: 99%

“…But they are still included in the study because from an implementational point of view while catching fish, non-fish species can be caught in the fishing nets as well and therefore it requires a method to separate fish and non-fish species. These fishes can be replaced with a database of other fish species as well by transferring the weights and biases of the neural network [82]. After the data collection, the images have been further resized for the experiment.…”

Section: Data Collection Filtering and Preprocessing With Esrganmentioning

confidence: 99%

Fish Species Identification on Low Resolution - A Study with Enhanced Super Resolution Generative Adversarial Network (ESRGAN), YOLO and VGG-16

Adhikary¹

2022

Preprint

View full text Add to dashboard Cite

A smart detection and recognition model for the species of a fish from camera footage is of urgent requirement as fishery contributes to a large portion of the world economy and these kinds of advanced models can aid fishermen on a large scale. Such models incorporating a pick-and-place machine can be very useful to sort different fish species in a bulk without human intervention and this can greatly reduce costs for large scale fishing industries. Existing methods for detecting and recognizing fish species have many limitations such as limited scalability, detection accuracy, failing to detect multiple species, degraded performance at a lower resolution, or pinpointing the exact location of the fish. By modifying the head of a very powerful deep learning model namely VGG-16 with pre-trained weights can be used to detect both the species of the fish and find the exact location of the fish in an image by implementing a modified YOLO to incorporate the bounding box regression head. We have proposed the usage of the ESRGAN algorithm along with the proposed neural network to amplify the image resolution by a factor of 4. With this method, the overall detection accuracy of 96.5% has been obtained. The experiment has been conducted based on a total of 9460 images spread across 9 species. After further improving the model, a pick-and-place machine could be integrated for very fast sorting of the fish according to their species in different large-scale fish industries.

show abstract

A Large-Scale Dataset for Fish Segmentation and Classification

Cited by 44 publications

References 14 publications

Classification of Fish Species with Image Data Using K-Nearest Neighbor

Classification of Fish Species with Image Data Using K-Nearest Neighbor

KeepNMax: Keep N Maximum of Epoch-Channel Ensemble Method for Deep Learning Models

Fish Species Identification on Low Resolution - A Study with Enhanced Super Resolution Generative Adversarial Network (ESRGAN), YOLO and VGG-16

Contact Info

Product

Resources

About