Aquarium Family Fish Species Identification System Using Deep Neural Networks Nour Eldeen M. Khalifa 1,2(&) , Mohamed Hamed N. Taha 1,2 , and Aboul Ella Hassanien 1,2 1 Information Technology Department, Faculty of Computers and Information, Cairo University, Giza, Egypt {nourmahmoud,mnasrtaha,aboitcairo}@cu.edu.eg 2 Scientific Research Group in Egypt (SRGE), Giza, Egypt http://www.egyptscience.net Abstract. 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. Keywords: Deep learning Á Deep neural Á Fish identification Convolutional neural networks 1 Introduction Fish species observation and identification in the aquarium are considered very informative for tourists. The aquarium is equipped with a camera and when a fish passes in front of it, an identification system is triggered to classify the fish and display information on the screen as illustrated in Fig. 1 and considered one of the main motivation of this research. Also, this research area is important for academic researchers like ocean scientists and biologists. Commercial applications like fish farming depend on fish species observation to achieve their benefits. This involves time-consuming and destructive measures to get physical samples and visual census. However, these approaches are still common. Fish species recognition is a challenging issue for research. Great challenges for fish recognition appear in the special properties of underwater videos and images. Prior fish recognition, researchers were limited to constrained environments before fish recognition [1]. The focus of the most recognition research is on ground objects. © Springer Nature Switzerland AG 2019 A. E. Hassanien et al. (Eds.): AISI 2018, AISC 845, pp. 347–356, 2019. https://doi.org/10.1007/978-3-319-99010-1_32