Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{189130,
        author = {Anmol Mishra and Deepak Pant and Ankit Singh and Ahan Raj},
        title = {Fish Species Identification: An AI & Mobile Solution},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {7},
        pages = {5129-5135},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=189130},
        abstract = {The marine ecosystem is essential for supporting millions of fishermen and coastal communities by providing livelihoods, nutrition, and economic stability. In India, fisheries play a significant role in the national GDP and employment, making timely and accurate species-level catch reporting increasingly important. Even with marine advisory systems like those developed by INCOIS, there are still gaps in real-time data collection and reliable species identification. These gaps often result in incomplete records and limit the effectiveness of fisheries planning, conservation efforts, and policy-making.
This review looks at a proposed Android-based mobile application that uses Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL) to automate fish species identification and digital catch reporting. The system uses the lightweight MobileNetV2 architecture. It is trained on a curated and expert-validated dataset of fish images, and converted to TensorFlow Lite. This allows for fast, offline inference directly on fishermen’s smartphones. This makes the solution practical for coastal areas with low connectivity.
The application uses SQLite for offline data storage, allowing fishermen to reliably record catch details even in remote areas without internet access, while Firebase enables secure cloud synchronization once a network is available, ensuring that all data is safely backed up and accessible for analysis. GPS and weather APIs automatically add precise location, time, and environmental conditions to each catch record, providing valuable context for each observation. By combining fish species recognition with detailed contextual information, the system improves the reliability and analytical value of fisheries data, supporting effective ecosystem monitoring and sustainable fisheries management practices at regional and national levels.},
        keywords = {Fish Species, Machine Learning, Image Classification, Grad-CAM, Artificial Intelligence},
        month = {December},
        }