From: Fish species classification using a collaborative technique of firefly algorithm and neural network
Author | Methodology | Benefits | Drawbacks |
---|---|---|---|
Fouad et al. [10] | Scale Invariant Feature Transform (SIFT) along with Speeded up Robust Features (SURF) followed by Support Vector machine (SVM) | Experimentation had illustrated that 94.4% detection accuracy was attained by the fish classification utilizing SURF and SVM | The presented work was not utilized in a real-time environment |
Qin et al. [17] | Framework centered upon Principal Component Analysis (PCA) | SVM was utilized as a machine learning classifier that illustrated 98.64% classification accuracy against a real-world fish recognition dataset | The filters of the proffered system were not as nice |
Siddiqui et al. [18] | CNN | For the fish captured by the Western Australia coast, this strategy depicted 94.3% classification accuracy | In this work, the training data used was limited |
Lakshmi et al. [20] | Gaussian mixture model + SURF | Utilizing multiclass-SVM (MSVM), the testing was executed which exhibited 88.9% classification accuracy | High false positives were possessed by this method |
Jalal et al. [21] | YOLO deep neural network | Fish detection F-scores of 95.47% along with 91.2% were attained by this method, whilst fish species classification accuracies of 91.64% along with 79.8% were obtained on datasets correspondingly | More computational power was utilized by the proposed system since it comprised a complex machine learning tool when contrasted to traditional computer vision along with image processing approaches |
Villon et al. [19] | Few Shot Learning (FSL) | This work found that the classic DL approach was outperformed by FSL in situations along with good classification accuracy was offered | The annotated images in this work were restricted |