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{187565,
        author = {Bibi Safura and Amulya TS and Chaitanya N and Deepika and Asst Professor Niveditha V K},
        title = {Embedded Intelligent Microscopy System for Identification and Counting of Microscopic Marine Organisms},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {6},
        pages = {5854-5856},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=187565},
        abstract = {The design, implementation, and assessment of an Embedded Intelligent Microscopy System (EIMS) for the automatic identification and counting of tiny sea animals (phytoplankton and zooplankton) are presented in this study. A low-cost optical microscope, on board image capturing, real-time preprocessing, and a lightweight convolutional neural network for object recognition and classification implemented on an embedded platform are all integrated into the system. We outline the model architecture and optimization for embedded inference, evaluation metrics, training dataset preparation, imaging pipeline, and hardware design. While operating at 7-12 frames per second on the target embedded platform, results on a mixed dataset of typical coastal microplankton show classification accuracy of 91.7% (macro-averaged F1 = 0.90) and counting error (mean absolute percentage error) of 6.8% on held- out test samples. We talk about future work toward in-situ deployment on autonomous sampling devices, ecological utility, and system limits.},
        keywords = {Embedded microscopy, marine microorganisms, plankton identification, lightweight CNN, automated counting, in-situ monitoring.},
        month = {November},
        }