Copyright © 2025 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{181867,
        author = {Rehana Banu and Tasneem Sultana and Anushka S. Kalla and Prof. Supriya Bagewadi},
        title = {Intelligent Mobile Plant Identifier: A Deep Learning Approach for Offline Plant Recognition and Data Display.A Comprehensive Review},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {2},
        pages = {103-110},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=181867},
        abstract = {Fields including agriculture, botany, biodiversity monitoring, and environmental education all depend on accurate plant species identification. Traditional approaches are trustworthy, but they are frequently laborious, need specialized knowledge, and are not available to the general public. Recent developments in mobile computing and artificial intelligence have produced intelligent plant identification systems that can identify species from visual inputs.  Nevertheless, a lot of these apps rely significantly on internet access, which restricts their use in distant or field-based environments. With an emphasis on deep learning methods and the incorporation of offline capabilities, this review offers a thorough examination of mobile-based plant recognition systems. Examining several convolutional neural network (CNN) designs, image preprocessing techniques, and datasets utilized in the field, the research assesses each one's performance, effectiveness, and suitability for deployment on devices with limited resources. It also draws attention to the difficulties of offline inference, including limited local data storage, real-time computation, and model compression.  The study addresses present limits and new trends, such as federated learning, on-device model training, and integration with augmented reality, by carefully comparing existing applications and approaches. The results highlight the increasing possibility of scalable, intelligent, and intuitive plant identification systems that function without internet connectivity, opening the door for greater accessibility and influence across fields.},
        keywords = {Plant, Smartphone, Image Processing, Mobile, Deep Learning},
        month = {June},
        }