Skip to main content
Springer Nature Link
Log in

Deep learning with invariant feature based species classification in underwater environments

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Researchers are paying more attention these days to research on the detection and classification of underwater species from images. The main goal of the researchers is to make a pre-processing algorithm that uses an enhancement mechanism to find the exact region of species. It is crucial for marine researchers and scientists to estimate the region of species for classification on a regular basis, but this is a challenging task due to uncleanly captured images. The main causes of such a problem are variation in light of the underwater environment, species concealment, irregular backgrounds, low resolution, and indirect variations between some species patterns. To address these issues, we propose an Invariant Feature-based Species Classification (IFSC) model that employs a pattern-net-based Convolutional Neural Network (CNN) as a deep learning model in an underwater environment. We focused on two types of species: octopus and crabs, each with eight subclasses, and the dataset used was self-collected from the Poppe Image Marine Iconography. To achieve maximum classification accuracy, this study focuses on appropriate segmentation and invariant feature extraction. Following the extraction of invariant features, the concept of a genetic algorithm (GA) is used to select only the most relevant features based on their class. The invariant feature extraction approach known as the Speed Up Robust Feature (SURF) descriptor performed well, and the model achieved an overall accuracy of 95.04%, which is higher than the existing work of 1.71%. As far as we know, the results we got are the best ones that have been published on the collected dataset in the past few years, which shows that our strategy works better than others.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Algorithm 1
Algorithm 2
Algorithm 3
Fig. 4
Fig. 5
Algorithm 4
Fig. 6
Algorithm 5
Fig. 7
Algorithm 6
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14

Similar content being viewed by others

References

  1. Ancuti CO, Ancuti C, De Vleeschouwer C, Bekaert P (2018) Color balance and fusion for underwater image enhancement. IEEE Trans Image Process 27(1):379–393

    Article  ADS  MathSciNet  PubMed  Google Scholar 

  2. Bazeille S, Quidu I, Jaulin L, Malkasse JP (2006) Automatic underwater image pre-processing. In CMM’06 (p. xx)

  3. Gao Y, Wang J, Li H, Feng L (2019) Underwater image enhancement and restoration based on local fusion. J Electron Imaging 28(4):043014

    Article  ADS  Google Scholar 

  4. Garg D, Garg NK, Kumar M (2018) Underwater image enhancement using blending of CLAHE and percentile methodologies. Multimedia Tools Applic 77(20):26545–26561

    Article  Google Scholar 

  5. Han F, Yao J, Zhu H, Wang C (2020) Marine organism detection and classification from underwater vision based on the deep CNN method. Math Problems Eng 2020

  6. Iqbal N, Ali S, Khan I, Lee BM (2019) Adaptive edge preserving weighted mean filter for removing random-valued impulse noise. Symmetry 11(3):395

    Article  ADS  Google Scholar 

  7. Jalal A, Salman A, Mian A, Shortis M, Shafait F (2020) Fish detection and species classification in underwater environments using deep learning with temporal information. Ecol Inform 57(101):088

    Google Scholar 

  8. Jin L, Liang H (2017) Deep learning for underwater image recognition in small sample size situations. In OCEANS 2017-Aberdeen, IEEE, pp. 1–4

  9. Kaur M, Vijay S (2022) Underwater images quality improvement techniques for feature extraction based on comparative analysis for species classification. Multimedia Tools Applic 81(14):19445–19461

    Article  Google Scholar 

  10. LeCun Y, Boser B, Denker JS, Henderson D, Howard RE, Hubbard W, Jackel LD (1989) Backpropagation applied to handwritten zip code recognition. Neural Comput 1(4):541–551

    Article  Google Scholar 

  11. Liu S, Li X, Gao M, Cai Y, Nian R, Li P, Lendasse A (2018) Embedded online fish detection and tracking system via YOLOv3 and parallel correlation filter. OCEANS 2018 MTS/IEEE Charleston. IEEE, pp 1–6

  12. Ning X, Tian W, Yu Z, Li W, Bai X, Wang Y (2022) HCFNN: high-order coverage functions neural network for image classification. Pattern Recogn 131(108):873

    Google Scholar 

  13. Salman A, Siddiqui SA, Shafait F, Mian A, Shortis MR, Khurshid K, Schwanecke U (2020) Automatic fish detection in underwater videos by a deep neural network-based hybrid motion learning system. ICES J Mari Sci 77(4):1295–1307

  14. Salman A, Jalal A, Shafait F, Mian A, Shortis M, Seager J, Harvey E (2016) Fish species classification in unconstrained underwater environments based on deep learning. Limnol Oceanogr: Methods 14(9):570–585

    Article  Google Scholar 

  15. Schettini R, Corchs S (2010) Underwater image processing: state of the art of restoration and image enhancement methods. EURASIP J Adv Signal Process 2010:1–14

    Article  Google Scholar 

  16. Spampinato C, Giordano D, Di Salvo R, Chen-Burger YHJ, Fisher RB, Nadarajan G (2010) Automatic fish classification for underwater species behavior understanding. In: Proceedings of the first ACM international workshop on Analysis and retrieval of tracked events and motion in imagery streams, pp 45–50

  17. Sung M, Yu SC, Girdhar Y (2017) Vision based real-time fish detection using convolutional neural network. In OCEANS 2017-Aberdeen. IEEE, pp 1–6

  18. Verma K, Singh BK, Thoke AS (2015) An enhancement in adaptive median filter for edge preservation. Procedia Comput Sci 48:29–36

    Article  Google Scholar 

  19. Villon S, Iovan C, Mangeas M, Claverie T, Mouillot D, Villéger S, Vigliola L (2021) Automatic underwater fish species classification with limited data using few-shot learning. Ecol Inform 63(101):320

    Google Scholar 

  20. Wang C, Wang X, Zhang J, Zhang L, Bai X, Ning X, ..., Hancock E (2022) Uncertainty estimation for stereo matching based on evidential deep learning. Pattern Recogn 124:108–498

  21. Wang N, He M, Sun J, Wang H, Zhou L, Chu C, Chen L (2019) IA-PNCC: noise processing method for underwater target recognition convolutional neural network. Comput Mater Continua 58(1):169–181

    Article  Google Scholar 

  22. Xu W, Matzner S (2018) Underwater fish detection using deep learning for water power applications. In 2018 International conference on computational science and computational intelligence (CSCI). IEEE, pp 313–318

  23. Yang M, Sowmya A (2015) An underwater color image quality evaluation metric. IEEE Trans Image Process 24(12):6062–6071

    Article  ADS  MathSciNet  PubMed  Google Scholar 

  24. Yang H, Li J, Shen S, Xu G (2019) A deep convolutional neural network inspired by auditory perception for underwater acoustic target recognition. Sensors 19(5):1104

    Article  ADS  PubMed  PubMed Central  Google Scholar 

  25. Zion B, Alchanatis V, Ostrovsky V, Barki A, Karplus I (2007) Real-time underwater sorting of edible fish species. Comput Electron Agric 56(1):34–45

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Uttarakhand Technical University Uttrakhand, Dehradun, India

    Maninder Kaur

  2. Tula’s Institute, Uttarakhand, Dehradun, India

    Sandip Vijay

Authors
  1. Maninder Kaur
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Sandip Vijay
    View author publications

    You can also search for this author inPubMed Google Scholar

Contributions

Maninder Kaur is a Doctoral Scholar in Uttrakhand Technical University. She has completed her Masters in Technology from Guru Nanak Dev University, Amritsar in year 2015.She has published 1 paper in SCI journal MTAP (Multimedia tools and applications) and 3 papers in international journals and also presented her paper in international conference held in Dehradun. She has successfully completed a two online courses one authorized by NORTHWESTERN UNIVERSITY” with Grade Achieved: 90.7% and other by “DUKE UNIVERSITY” with Grade Achieved: 81.0%. Currently working as lecturer in Mehr Chand Polytechnic College Jalandhar, Punjab. Author collected the most of the data. Simulated the data using surf algorithm.

Sandip Vijay is the Senior Member of IEEE(USA), NSBE (USA), IANEG(USA), ISOC (USA), Life Member of ISTE (INDIA) and Fellow of ACEEE, Finland, has published over one hundred fifty research papers in national and international journals (SCI/SCOPUS)/conferences and IEEE proceeding publication in field of Wireless & Digital Communication Network, He completed his Doctorate in 2011 from I.I.T. Roorkee in the field of Wireless Computing under Ministry of HRD, Government of India fellowship.

Corresponding author

Correspondence to Maninder Kaur.

Ethics declarations

Conflict of interest

On behalf of all authors, the corresponding author states that there is no conflict of interest.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Kaur, M., Vijay, S. Deep learning with invariant feature based species classification in underwater environments. Multimed Tools Appl 83, 19587–19608 (2024). https://doi.org/10.1007/s11042-023-15896-8

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-023-15896-8

Keywords