An Automated Fish Species Identification System Based on Crow Search Algorithm

  • Gehad Ismail SayedEmail author
  • Aboul Ella Hassanien
  • Ahmed Gamal
  • Hassan Aboul Ella
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 723)


This paper proposed an automated fish species identification system based on a modified crow search optimization algorithm. Median filtering is applied for image smoothing and removing noise through reducing the variation of intensities between the neighbors. Then, a k-mean clustering algorithm is used to segment the fish image into multiple segments. Shape-based and texture-based feature extraction process for classification is presented. A new modified binary version of crow search algorithm is proposed to reduce the data dimensionality of the extracted features. Finally, support vector machine and decision trees are implemented for classification and the fish species are classified based on either their class including Actinopterygii and Chondrichthyes or based on their order. Total of 270 images with different species, classes and orders are used for evaluation of the proposed system. The experimental results show that the proposed system achieves the highest classification accuracy compared to state-of-the-art algorithms. Also, the results show that the overall fish species identification system obtains on average of 10 folds, 96% classification accuracy for classification based on class and 74% for classification based on fish order.


Crow Search Algorithm (CSA) Image classification Fish identification Feature selection 


  1. 1.
    Bridget, B., Junguk, C., Deborah, G., Ryan, K.: Field programmable gate array (FPGA) based fish detection using haar classifiers. In: American Academy of Underwater Sciences, Georgia, USA, pp. 1–8 (2009)Google Scholar
  2. 2.
    Sergio, B.: Fish age classification based on length, weight, sex and otolith morphological features. Fish. Res. 84(2), 270–274 (2007)CrossRefGoogle Scholar
  3. 3.
    Cabreira, A.G., Tripode, M., Madirolas, A.: Artificial neural networks for fish-species identification. ICES J. Mar. Sci. 66(6), 1119–1129 (2009)CrossRefGoogle Scholar
  4. 4.
    Alsmadi, M.K.: Fish recognition based on robust features extraction from size and shape measurements using neural network. J. Comput. Sci. 6, 1088–1094 (2010)CrossRefGoogle Scholar
  5. 5.
    Hoang, T., Lock, K., Mouton, A., Goethals, L.M.: Application of classification trees and support vector machines to model the presence of macroinvertebrates in rivers in Vietnam. Ecol. Inf. 5(2), 140–146 (2010)CrossRefGoogle Scholar
  6. 6.
    Cato, S., Bjorn, T., Darren, W., Overdal, J.: Automatic species recognition, length measurement and weight determination, using the catchmeter computer vision system. In: International Council for Exploration of the Sea, vol. 6, pp. 1–10 (2006)Google Scholar
  7. 7.
    Ogunlana, S., Olabode, O., Oluwadare, S., Iwaskoun, G.: Fish classification using support vector machine. Afr. J. Comput. ICT 8(2), 1–8 (2006)Google Scholar
  8. 8.
    Hu, J., Li, D., Duan, Q., Han, Y., Chen, G., Si, X.: Fish species classification by color, texture and multi-class support vector machine using computer vision. Comput. Electron. Agric. 88, 133–140 (2012)CrossRefGoogle Scholar
  9. 9.
    Hossain, E., Alam, S.M.S., Ali, A.A., Amin, M.A.: Fish activity tracking and species identification in underwater video. In: 2016 5th International Conference on Informatics, Electronics and Vision (ICIEV), pp. 62–66 (2016)Google Scholar
  10. 10.
    Fouad, M.M., Zawbaa, H.M., El-Bendary, N., Hassanien, A.E.: Automatic Nile Tilapia fish classification approach using machine learning techniques. In: 13th International Conference on Hybrid Intelligent Systems (HIS 2013), pp. 173–178 (2013)Google Scholar
  11. 11.
    Askarzadeh, A.: A novel metaheuristic method for solving constrained engineering optimization problems: crow search algorithm. Comput. Struct. 169, 1–12 (2016)CrossRefGoogle Scholar
  12. 12.
    Hunter, R.: Photo electric color difference meter. J. Opt. Soc. America 48(12), 985–995 (1958)CrossRefGoogle Scholar
  13. 13.
    Singh, N., Singh, D.: The improved k-means with particle swarm optimization. J. Inf. Eng. Appl. 3(11), 2224–5782 (2013)Google Scholar
  14. 14.
    Haralick, R., Shanmugam, K., Dinstein, I.: Textural features for image classification. IEEE Trans. Syst. Man Cybern. 3(6), 612–621 (1973)Google Scholar
  15. 15.
    Agrawal, R.: First and second order statistics features for classification of magnetic resonance brain images. J. Sig. Inf. 3, 146–153 (2012)Google Scholar
  16. 16.
    Sayed, G.I., Hassanien, A., Azar, A.: Feature selection via a novel chaotic crow search algorithm. Neural Comput. Appl. 1–18 (2017)Google Scholar
  17. 17.
    Sayed, G.I., Hassanien, A.: Moth-flame swarm optimization with neutrosophic sets for automatic mitosis detection in breast cancer histology images. Appl. Intell. 47(2), 397–408 (2017)CrossRefGoogle Scholar
  18. 18.
    Sayed, G.I., Darwish, A., Hassanien, A.: Quantum multiverse optimization algorithm for optimization problems. Neural Comput. Appl. 1–18 (2017)Google Scholar
  19. 19.
    Fish identification tools for biodiversity and fisheries assessments Review and guidance for decision-maker. FAO Fisheries and Aquaculture Technical paper, paper number 545 (2017).

Copyright information

© Springer International Publishing AG 2018

Authors and Affiliations

  1. 1.Faculty of Computers and InformationCairo UniversityCairoEgypt
  2. 2.Faculty of Veterinary MedicineCairo UniversityCairoEgypt
  3. 3.Scientific Research Group in Egypt (SRGE)CairoEgypt

Personalised recommendations