Fish detection and identification are important steps towards monitoring fish behavior. The importance of such monitoring step comes from the need for better understanding of the fish ecology and issuing conservative actions for keeping the safety of this vital food resource. The recent advances in machine learning approaches allow many applications to easily analyze and detect a number of fish species. The main competence between these approaches is based on two main detection parameters: the time and the accuracy measurements. Therefore, this paper proposes a fish detection approach based on BAT optimization algorithm (BA). This approach aims to reduce the classification time within the fish detection process. The performance of this system was evaluated by a number of well-known machine learning classifiers, KNN, ANN, and SVM. The approach was tested with 151 images to detect the Nile Tilapia fish species and the results showed that k-NN can achieve high accuracy 90 %, with feature reduction ratio close to 61 % along with a noticeable decrease in the classification time.
CITATION STYLE
Fouad, M. M., Zawbaa, H. M., Gaber, T., Snasel, V., & Hassanien, A. E. (2016). A fish detection approach based on BAT algorithm. In Advances in Intelligent Systems and Computing (Vol. 407, pp. 273–283). Springer Verlag. https://doi.org/10.1007/978-3-319-26690-9_25
Mendeley helps you to discover research relevant for your work.