Home⇛PUP Journal of Science and Technology⇛vol. 14 no. 1 (2021)

CAMARINE: A FISH SPECIES RECOGNITION SYSTEM THROUGH YOU ONLY LOOK ONCE

Prince Jewel C Federe | Andrew Emil M Pagador | Avegail O Ruiz

Discipline: Engineering

 

Abstract:

Data collection for marine sciences has always been arduous, mainly because of cost. The higher the cost is, the slower the growth of knowledge. To ease that cost, Camarine was built. An application for fish species recognition, Camarine used the algorithm You Only Look Once (YOLO) to seep through convolutional layers to detect and identify fish species. Twelve species of fish were categorized according to likeness and lack thereof. Over 4800 images were augmented to sport better results for the trained model. For testing, around 600 images were collected in various locations, including experiments done in a controlled environment. Results in detection showed an average of 88.63%, while the results in identification showed an average of 88.10%. For fishes of different appearances but the same species, the recorded accuracy was 92.66%. And for fishes of similar appearance but different species, the recorded accuracy was 86.60%. And finally, for general identification, 90.83% was the recorded accuracy. This all cumulates to the said 88.10% identification accuracy. Indeed, YOLO works well with identification, but this remains untested against turbid underwater images.



References:

  1. Alsmadi, M. K., & Almarashdeh, I. (2020). A survey on fish classification techniques. Journal of King Saud University - Computer and Information Sciences,  34(5), 1625 1638. https://doi.org/10.1016/j.jksuci.2020.07.005
  2. Ancuti, C., Ancuti, C. O., Haber, T., & Bekaert, P. (2012). Enhancing underwater images and videos by fusion. In 2012 IEEE conference on computer vision and pattern recognition (pp. 81-88). IEEE.  
  3. Boca Chica Baits. (2019). Caudal fin throttle fin - An article on the different types of caudal fins and how fish use them. Retrieved 5 June 2021, from https://bocachicabaits.com/blogs/news/caudal-fin-throttle-fin
  4. Bochkovskiy, A., Wang, C. Y., & Liao, H. Y. M. (2020). Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934.
  5. Bouchard, L. (2020). What is the YOLO algorithm?  Introduction to You Only Look Once, Real-time object detection. What is Artificial Intelligence. https://medium.com/whatis-artificial-intelligence/what-is-the-yolo-algorithm-introduction-to-you-only-lookonce-real-time-object-detection-f26aa81475f2.
  6. Brownlee, J. (2020). How to calculate precision, recall, and F-measure for imbalanced classification. Machine Learning Mastery. Retrieved January 18, 2022, from https://machinelearningmastery.com/precision-recall-and-f-measure-forimbalanced-classification/
  7. Capuli, E., & Luna, S. (2009). Aspidontus taeniatus summary page. Retrieved 11 May 2021, from https://www.fishbase.se/summary/Aspidontus-taeniatus.html
  8. Chandra, B. (2021). A beginners guide to Computer Vision (Part 4)- Pyramid. Medium. Retrieved November 15, 2021, from https://medium.com/analytics-vidhya/a beginners-guide-to-computer-vision-part-4-pyramid-3640edeffb00
  9. Chen, J. W., Lin, W. J., Cheng, H. J., Hung, C. L., Lin, C. Y., & Chen, S. P. (2021). A smartphone-based application for scale pest detection using multiple-object detection methods. Electronics, 10(4), 372. https://doi.org/10.3390/electronics10040372
  10. Cui, S., Zhou, Y., Wang, Y., & Zhai, L. (2020). Fish detection using deep learning. Applied Computational Intelligence and Soft Computing, 2020, 1–13. https://doi.org/10.1155/2020/3738108
  11. dos Santos, A. A., & Gonçalves, W. N. (2019). Improving Pantanal fish species recognition through taxonomic ranks in convolutional neural networks. Ecological Informatics, 53, 100977. https://doi.org/10.1016/j.ecoinf.2019.100977
  12. Fu, H., Song, G., & Wang, Y. (2021). Improved YOLOv4 marine target detection combined with CBAM. Symmetry, 13(4), 623. MDPI AG. Retrieved from http://dx.doi.org/10.3390/sym13040623
  13. Gad, A. (2020, October). Evaluating object detection models using Mean Average Precision (mAP). PaperspaceBlog. https://blog.paperspace.com/mean-average precision/. Garcia, P. (2021). What are caudal fins? Retrieved 5 June 2021, from https://www.allthingsnature.org/what-are-caudal-fins.htm
  14. Garrison, T. S. (2015). Chapter 2 History. In Oceanography: An invitation to marine science (9th ed.). Essay, Cengage Learning.
  15. Gholamy, A., Kreinovich, V., & Kosheleva, O. (2018). Why 70/30 or 80/20 relation between training and testing sets: A pedagogical explanation. International Journal of Intelligent Technologies & Applied Statistics, 11(2).
  16. Google Developers. Classification: Precision and Recall | Machine Learning Crash Course. (n.d.). Google Developers. Retrieved January 18, 2022, from https://developers.google.com/machine-learning/crashcourse/classification/precision-and-recall
  17. 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. Ecological Informatics, 57, 101088. https://doi.org/10.1016/j.ecoinf.2020.101088
  18. Jiang, Z., Zhao, L., Li, S., & Jia, Y. (2020). Real-time object detection method based on improved YOLOv4-tiny. arXiv preprint arXiv:2011.04244.
  19. Kalhagen, E. S. & Olsen, Ø. L. (2020). Hierarchical fish species detection in real-time video using YOLO (Master's thesis). University of Agder, Grimstad.
  20. Kang & Atul, (2019, August 19). Gaussian Pyramid. TheAILearner. Retrieved November 15, 2021, from https://theailearner.com/tag/gaussian-pyramid/
  21. Kennedy, J. (2019). What are the basics of fish anatomy? Retrieved 5 June 2021, from https://www.thoughtco.com/fish-anatomy-2291578
  22. Liu, L., Ouyang, W., Wang, X., Fieguth, P., Chen, J., Liu, X., & Pietikäinen, M. (2020). Deep learning for generic object detection: A survey.  International Journal of Computer Vision,  128, 261-318. https://doi.org/10.1007/s11263-019-01247-4
  23. Mahmood, Z., Muhammad, N., Bibi, N., Malik, Y. M., & Ahmed, N. (2018). Human visual enhancement using multi scale retinex. Informatics in Medicine Unlocked, 13, 9–20. https://doi.org/10.1016/j.imu.2018.09.001
  24. Mohamed, H. E. D., Fadl, A., Anas, O., Wageeh, Y., ElMasry, N., Nabil, A., & Atia, A. (2020). MSR-YOLO: Method to enhance fish detection and tracking in fish farms Procedia Computer Science, 170, Retrieved from https://doi.org/10.1016/j.procs.2020.03.123539–546.
  25. New Jersey Sea Grant Consortium [NJSGC]. (2010). Fish morphology. Retrieved 11 May 2021, from http://njseagrant.org/wp-content/uploads/2014/03/fish_morphology.pdf
  26. On The Water [OTW]. (2020, December). Identifying bluefin vs yellowfin tuna. https://www.onthewater.com/identifying-bluefin-vs-yellowfin-tuna
  27. Oosting, T., Star, B., Barrett, J. H., Wellenreuther, M., Ritchie, P. A., & Rawlence, N. J. (2019). Unlocking the potential of ancient fish DNA in the genomic era. Evolutionary Applications, 12(8), 1513–1522. https://doi.org/10.1111/eva.12811
  28. Petro, A. B., Sbert, C., & Morel, J. M. (2014). Multiscale retinex. Image Processing On Line, 4, 71–88. https://doi.org/10.5201/ipol.2014.107
  29. Priyankan, K., & Fernando, T. G. I. (2021). Mobile application to identify fish species using YOLO and convolutional neural networks. Lecture Notes in Networks and Systems, 303–317. https://doi.org/10.1007/978-981-33-4355-9_24
  30. Rathi, D., Jain, S., & Indu, S. (2017). Underwater fish species classification using convolutional neural network and deep learning. In 2017 Ninth International Conference on Advances in Pattern Recognition (ICAPR), 1-6. IEEE 
  31. Raza, K., & Hong, S. (2020). Fast and accurate fish detection design with improved YOLO-v3 model and transfer learning. International Journal of Advanced Computer Science and Applications, 11(2). https://doi.org/10.14569/ijacsa.2020.0110202
  32. Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You Only Look Once: Unified, real-time object detection. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 779-788). https://doi.org/10.1109/cvpr.2016.91
  33. Sharpe, S. (2020). The seven types of fish mouths and how they are used. Retrieved 11 May 2021, from https://www.thesprucepets.com/fish-mouth-types-1381813#id-
  34. Sigwart, J. D., Blasiak, R., Jaspars, M., Jouffray, J. B., & Tasdemir, D. (2021). Unlocking the potential of marine biodiscovery. Natural Product Reports.
  35. Snyderman, M. (2003, May 6). Form and function: Sea creature shapes examined. DiveTraining. https://blog.roboflow.com/train-yolov4-tiny-on-custom-data-lightingfast-detection/
  36. Solawetz, J. (2021, March 8). Train YOLOv4-tiny on custom data - lightning fast object detection. Roboflow Blog. https://dtmag.com/thelibrary/form-function-sea-creatureshapes-examined/
  37. Stanford University. (2002). The Laplacian Pyramid. Stanford Exploration Project. Retrieved November 15, 2021, from http://sepwww.stanford.edu/data/media/public/sep/morgan/texturematch/paper_html/node3.html
  38. Torres, S.K., & Santos, B.S. (2019). Species identification among morphologically-similar Caranx species. Turkish Journal of Fisheries and Aquatic Sciences, 20(2), 159-169.
  39. Villon, S., Mouillot, D., Chaumont, M., Darling, E. S., Subsol, G., Claverie, T., & Villéger,  S. (2018). A deep learning method for accurate and fast identification of coral reef fish underwater images. Ecological Informatics, 48, 238–244. https://doi.org/10.1016/j.ecoinf.2018.09.007
  40. Wood, T. (2020, August 7). F-score. DeepAI. Retrieved January 18, 2022, from https://deepai.org/machine-learning-glossary-and-terms/f-score
  41. Wu, L., Ma, J., Zhao, Y., & Liu, H. (2021). Apple detection in complex scene using the improved YOLOv4 model. Agronomy, 11(3), 476. MDPI AG. Retrieved from http://dx.doi.org/10.3390/agronomy11030476
  42. Zhou, C., Yang, X., Zhang, B., Lin, K., Xu, D., Guo, Q., & Sun, C. (2017). An adaptive image enhancement method for a recirculating aquaculture system. Scientific Reports, 7(1). https://doi.org/10.1038/s41598-017-06538-9

Tools


Copyright © 2024  KITE Digital Educational Solutions |  Exclusively distributed by CE-Logic