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{204075,
        author = {Ms. Pawar Poornima Gangadhar and Mr. Naik Smit Sujit and Mr. More Parth Manoj and Mr. Patil Soham Hemant and Mr. Narvekar Ronit Mahesh},
        title = {A Real-Time Hand Gesture Based Fruit Learning Platform to Support Deaf Communication Using MediaPipe, SVM, and Django},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {1},
        pages = {2906-2911},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=204075},
        abstract = {Deaf people often find it hard to communicate with hearing individuals because they don’t share the same way of expressing themselves. To help with this, this project suggests a web-based learning tool that teaches American Sign Language (ASL) signs for different fruits. It uses instructional videos to show how to make the signs, and then tests the learner’s ability by using a live camera. The homepage of the platform introduces ten fruit signs through tutorials, and then lets users try making them. A module based on Google MediaPipe tracks hand movements and identifies 21 key points on each hand in real time. These points are turned into a detailed 117-dimensional feature vector, which is then classified by a Support Vector Machine with an RBF kernel. When the system recognizes a sign with enough confidence, it displays the fruit’s name on the screen, shows a picture of the fruit on top of the video, and also speaks the name aloud using a text-to-speech feature. The training data was collected by having one team member perform each sign, then breaking the videos into grayscale frames and applying a six-fold data augmentation method. The final classifier shows good and reliable performance across all ten fruit signs under normal conditions, making it a useful tool for teaching sign language to deaf individuals.},
        keywords = {ASL Gesture Recognition, MediaPipe Hand Landmarks, Support Vector Machine, Django Web Framework, Deaf Learning Platform, Text-to-Speech, Real-Time Computer Vision.},
        month = {June},
        }