Accurate identification of fish species plays a crucial role in fisheries management and conservation. However, traditional methods struggle to address the diverse marine species found in India, resulting in inaccuracies and time-consuming processes. Manual identification by experts becomes particularly challenging, especially for large-scale conservation and monitoring efforts. To tackle this issue, we propose an Artificial Intelligence (AI) based framework for precise and efficient fish species identification in India. Our framework utilizes convolutional neural networks (CNNs) to extract features from fish images and employs the Random Forest Classifier for species identification. Trained on a comprehensive dataset encompassing various regions in India, our model achieved an impressive accuracy of 98.20 percent in rigorous testing, highlighting its effectiveness. Specifically, our proposed Random Forest Classifier exhibited remarkable accuracy in classifying fish species from grayscale images. By employing this AI framework, fish species identification in India can be significantly improved, leading to tangible benefits in fisheries management, conservation efforts, marine biology research, and aquaculture. Furthermore, the versatility of our approach allows its application to other countries with similar fish species diversity, offering potential solutions for real-world scenarios, such as underwater cameras.

Artificial Intelligence, Fish Species, Convolutional Neural Networks, Random Forest Algorithm, aquaculture research, identification, conservation, classification.

[1] M. Bhanumathi and B. Arthi, “Future Trends and Short-Review on Fish Species Classification Models Based on Deep Learning Approaches,” in 2022 International Conference on Augmented Intelligence and Sustainable Systems (ICAISS), 2022.
[2] J. Dewan, A. Gele, O. Fulari, B. Kabade and A. Joshi, “Fish Detection and Classification,” in 2022 6th International Conference On Computing, Communication, Control And Automation (ICCUBEA, 2022.
[3] V. Ananthan, “Fish Species Detection and Tracking Based on Fusion Intensity Entity Transformation using Optical Flow Algorithm,” in 2022 International Conference on Edge Computing and Applications (ICECAA), 2022.
[4] Y. Li, D. Zhu and H. Fan, “An Improved Faster RCNN Marine Fish Classification Identification Algorithm,” in 2021 2nd International Conference on Artificial Intelligence and Computer Engineering (ICAICE), 2021.
[5] D. F. Mujtaba and N. R. Mahapatra, “Fish Species Classification with Data Augmentation,” in 2021 International Conference on Computational Science and Computational Intelligence (CSCI), 2021.
[6] D. F. Mujtaba and N. R. Mahapatra, “Convolutional Neural Networks for Morphologically Similar Fish Species Identification,” in 2021 International Conference on Computational Science and Computational Intelligence (CSCI), 2021.
[7] Y. Cao, Q. Lei, T. Wei and H. Zhong, “A computer vision program that identifies and classifies fish species,” in 2021 International Conference on Electronic Information Engineering and Computer Science (EIECS), 2021.
[8] A. K. Agarwal, R. G. Tiwari, V. Khullar and R. K. Kaushal, “Transfer Learning Inspired Fish Species Classification,” in 2021 8th International Conference on Signal Processing and Integrated Networks (SPIN), 2021.
[9] B. V. Deep and R. Dash, “Underwater Fish Species Recognition Using Deep Learning Techniques,” in 2019 6th International Conference on Signal Processing and Integrated Networks (SPIN), 2019.
[10] M.-C. Chuang, J.-N. Hwang and K. Williams, “Supervised and Unsupervised Feature Extraction Methods for Underwater Fish Species Recognition,” in 2014 ICPR Workshop on Computer Vision for Analysis of Underwater Imagery, 2014.
[11] I. T. &. C. J. Jolliffe, “Principal component analysis: a review and recent developments,” Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, vol. 374, no. 2065, p. 20150202, 2016.
[12] S. S. S. N. M. &. B. D. K. Mandal, “Fish Species Classification Using Deep Learning and Random Forest Techniques,” in 11th International Conference on Computing, Communication and Networking Technologies (ICCCNT), 2020.
[13] Z. Rasheed, “PCA Based Dimensionality Reduction for the Classification of Hyperspectral Data,” in 2015 IEEE 12th International Conference on e-Business Engineering, 2015.
[14] Y. &. H. T. S. Chen, “Fish species recognition by a random forest classifier,” in IEEE International Conference on Multimedia & Expo Workshops (ICMEW), 2017.
[15] C. J. C. Z. Z. L. X. &. W. Z. Zhang, “A fish species identification and classification method based on deep learning and random forest,” Aquaculture, vol. 531, p. 735962, 2021.
[16] R. &. V. S. Loh, “Random forest classification of fish images for underwater species recognition,” in In International Conference on Image Processing, 2013.
[17] M. Kaufmann, Data Mining: Practical Machine Learning Tools and Techniques, ScienceDirect, 2016.
[18] S. Khalifa, “An Efficient PCA-SVM Model for the Recognition of Five Fish Species Using Their Images,” International Journal of Computer Science and Network Security, vol. 17, no. 10, pp. 20-25, 2017.
[19] A. S. K. K. A. A. A. V. S. a. B. M. J. N. N, “Convolutional Neural Networks (CNN) based Marine Species Identification,” Pudukkottai, 2022.
[20] R. P. F. A. I. S. a. A. J. Z. Abidin, “Betta Fish Image Identification using Feature Extraction GLCM and K-Nearest Neighbour Classification,” in IEEE, Jakarta, 2022.