ICTACT Journal on Image and Video Processing

Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

Freshwater Fish Species Classification using Deep CNN Features


Affiliations
1 Department of Electrical and Electronics Engineering, Assam Don Bosco University, India
2 Department of Zoology, Bahona College, India
     

   Subscribe/Renew Journal


Deep-Learning and image processing have shown excellent performance in automated fish image classification and recognition task in recent years. In this research paper, we have come up with a novel deep-learning method based on CNN features extracted from deeper layer of a pretrained CNN architecture for automatic classification of eleven (11) indigenous fresh water fish species from India. We have utilized top three layers of a pretrained Resnet-50 model to extract features from fish images and an “ones for all SVM” classifier to train and test images based on the CNN features. This paper reports an exceptional result in overall classification performance on Fish-Pak dataset and on our own dataset. The proposed framework yields overall classification accuracy, precision and recall of 100% on our own data and a maximum of 98.74% accuracy on Fish-Pak dataset which is the best till date.

Keywords

Automatic Fish Detection, Fish Classification, Fish Species Recognition, Fish Database, Feature Extraction
Subscription Login to verify subscription
User
Notifications
Font Size

  • N.J.C. Strachan, “Recognition of Fish Species by Colour and Shape”, Image and Vision Computing, Vol. 11, pp. 2-10, 1993.

  • S. Cadieux, F. Michaud and F. Lalonde, “Intelligent System for Automated Fish Sorting and Counting”, Proceedings of International Conference on Intelligent Robots and Systems, pp. 1279-1284, 2000.

  • A. Rova, G. Mori and L. Dill, “One Fish, Two Fish, Butterfish, Trumpeter: Recognizing Fish in Underwater Video”, Proceedings of APR Conference on Machine Vision Applications, pp. 404-407, 2007.

  • C. Spampinato and Chen-Burger, “Automatic Fish Classification for Underwater Species Behavior Understanding”, Proceedings of International Conference on Analysis and Retrieval of Tracked Events and Motion in Imagery Streams, pp. 1-8, 2008.

  • M.K. Alsmadi and S.A. Noah, “Fish Classification based on Robust Features Extraction from Color Signature using Back-Propagation Classifier”, Journal of Computational Science, Vol. 7, pp. 52-65, 2011.

  • B. Benson and R. Kastner, “Field Programmable Gate Array (FPGA) Based Fish Detection Using Haar Classifiers”, American Academy of Underwater Sciences, Vol. 9, No. 2, pp. 1-15, 2009.

  • J. Hu, D. Li and X. Si, “Fish Species Classification by Color, Texture and Multi-Class Support Vector Machine using Computer Vision”, Computers and Electronics in Agriculture, Vol. 88, pp. 133-140, 2012.

  • M.M.M. Fouad, H.M. Zawbaa, N. El-Bendary and A.E. Hassanien, “Automatic Nile Tilapia fish Classification Approach using Machine Learning Techniques”, Proceedings of International Conference on Hybrid Intelligent Systems, pp. 173-178, 2013.

  • C. Pornpanomchai and W. Kitiyanan, “Shape- and Texture-Based Fish Image Recognition System”, Kasetsart Journal - Natural Science, Vol. 47, pp. 624-634, 2013.

  • M. Rodrigues and E. Carrano, “Evaluating Cluster Detection Algorithms and Feature Extraction Techniques in Automatic Classification of Fish Species”, Pattern Analysis and Applications, Vol. 18, pp. 1-13, 2014.

  • P.X. Huang and R.B. Fisher, “Hierarchical Classification with Reject Option for Live Fish Recognition”, Machine Vision and Application, Vol. 26, pp. 89-102, 2015.

  • P. Mathew and S. Elizabeth, “Fish Identification Based on Geometric Robust Feature Extraction from Anchor/Landmark Points”, Proceedings of International Conference on Image Processing and Machine Vision, pp. 1-14, 2017.

  • Jisha Jose and S. Sureshkumar, “Tuna Classification using Super Learner Ensemble of Region-Based CNN-Grouped 2D-LBP Models”, Information Processing in Agriculture, Vol. 9, pp. 1-13, 2021.

  • S.A. Siddiqui, A. Salman and E.S. Harvey, “Automatic Fish Species Classification in Underwater Videos: Exploiting Pretrained Deep Neural Network Models to Compensate for Limited Labelled Data”, ICES Journal of Marine Science, Vol. 75, pp. 374-389, 2017.

  • Y. Ma, P. Pengfei and Y. Tang, “Research on Fish Image Classification Based on Transfer Learning and Convolutional Neural Network Model”, Proceedings of International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery, pp. 850-855, 2018.

  • A. Salman, S. Maqbool and F. Shafait, “Real-Time Fish Detection in Complex Backgrounds using Probabilistic Background Modelling”, Ecological Informatics, Vol. 51, No. 2, pp. 44-51, 2019.

  • N.E. Khalifa and Aboul Ella, “Aquarium Family Fish Species Identification System Using Deep Neural Networks”, Proceedings of International Conference on Advanced Intelligent Systems and Informatics, pp. 1-13, 2018.

  • A. Jalal, S. Ajmal and F. Shafait, “Fish Detection and Species Classification in Underwater Environments using Deep Learning with Temporal Information”, Ecological Informatics. Vol. 57, pp. 1-14, 2020.

  • M.A. Iqbal and Z. Wang, “Automatic Fish Species Classification Using Deep Convolutional Neural Networks”, Wireless Personal Communications, Vol. 116, pp. 1043-1053, 2021.

  • S.Z.H. Shah, Malik Shahzaib Farooq and M. Muhammad, “Fish-Pak: Fish Species Dataset from Pakistan for Visual Features Based Classification”, Mendeley Data, Vol. 3, No. 2, pp. 1-14, 2019.

  • M.A. Islam and M.M. Rahman, “Indigenous Fish Classification of Bangladesh using Hybrid Features with SVM Classifier”, Proceedings of International Conference on Computer, Communication, Chemical, Materials and Electronic Engineering, pp. 1-7, 2019.

  • H.T. Rauf and Syed Ahmad Chan, “Visual Features based Automated Identification of Fish Species using Deep Convolutional Neural Networks”, Computers and Electronics in Agriculture, Vol. 167, pp. 1-18, 2019.

  • A. Banan, Amin Nasiri and A. Taheri-Garavand, “Deep Learning-Based Appearance Features Extraction for Automated Carp Species Identification”, Aquacultural Engineering, Vol. 89, pp. 1-17, 2020.

  • K. Dey, M.M. Hassan, M.M. Rana and M.H. Hena, “Bangladeshi Indigenous Fish Classification using Convolutional Neural Networks”, Proceedings of International Conference on Information Technology, pp. 899-904, 2021.

  • N.S. Abinaya and R. Sidharthan, “Naive Bayesian Fusion based Deep Learning Networks for Multisegmented Classification of Fishes in Aquaculture Industries”, Ecological Informatics, Vol. 61, pp. 1-15, 2021.

  • H. Wang, Y. Shi and H. Zhao, “Study on Freshwater Fish Image Recognition Integrating SPP and DenseNet Network”, Proceedings of IEEE International Conference on Mechatronics and Automation, pp. 1-8, 2020.

  • A. Krizhevsky and G. Hinton, “ImageNet Classification with Deep Convolutional Neural Networks”, Neural Information Processing Systems, Vol. 25, pp. 1-14, 2012.

  • K. He, X. Zhang, S. Ren and J. Sun, “Deep Residual Learning for Image Recognition”, Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, pp. 770-778, 2016.

  • Sinno Jialin and Qiang Yang, “A Survey on Transfer Learning”, IEEE Transactions on Knowledge and Data Engineering, Vol. 22, No. 1, pp. 1345-1359, 2010.

  • Hui-Hui and Po Ting. “The Effect of Different Deep Network Architectures upon CNN-Based Gaze Tracking”, Algorithms, Vol. 13, pp. 127-1136, 2020.


Abstract Views: 263

PDF Views: 1




  • Freshwater Fish Species Classification using Deep CNN Features

Abstract Views: 263  |  PDF Views: 1

Authors

Jayashree Deka
Department of Electrical and Electronics Engineering, Assam Don Bosco University, India
Shakuntala Laskar
Department of Zoology, Bahona College, India
Bikramaditya Baklial
Department of Zoology, Bahona College, India

Abstract


Deep-Learning and image processing have shown excellent performance in automated fish image classification and recognition task in recent years. In this research paper, we have come up with a novel deep-learning method based on CNN features extracted from deeper layer of a pretrained CNN architecture for automatic classification of eleven (11) indigenous fresh water fish species from India. We have utilized top three layers of a pretrained Resnet-50 model to extract features from fish images and an “ones for all SVM” classifier to train and test images based on the CNN features. This paper reports an exceptional result in overall classification performance on Fish-Pak dataset and on our own dataset. The proposed framework yields overall classification accuracy, precision and recall of 100% on our own data and a maximum of 98.74% accuracy on Fish-Pak dataset which is the best till date.

Keywords


Automatic Fish Detection, Fish Classification, Fish Species Recognition, Fish Database, Feature Extraction

References