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{206503,
        author = {Tabassum Nahid Sultana and Ayesha Kiran and Asra Fatima},
        title = {Multi-headed Convolutional Neural Network for Neuro Sign Interpretation from Complex Backgrounds},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {2},
        pages = {2427-2435},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=206503},
        abstract = {Sign language recognition systems are essential for facilitating communication between hearing-impaired individuals and the general population. However, existing systems often exhibit performance degradation across different skin tones and rely on suboptimal hand-crafted features. This paper presents a Convolutional Neural Network (CNN) based approach for recognizing static sign language gestures (alphabets and words) that addresses these limitations. The proposed system incorporates an adaptive pre processing filter that achieves skin tone-invariant gesture segmentation through colour space transformation and adaptive thresholding. A four-layer CNN architecture automatically learns hierarchical feature representations, eliminating the need for manual feature engineering. Experimental results demonstrate superior recognition accuracy and consistency across diverse skin tone categories compared to traditional methods. The system provides a practical, scalable solution for automated sign language interpretation in educational, healthcare, and public service settings, contributing to improved accessibility and social inclusion for the hearing-impaired community.},
        keywords = {Sign language recognition, CNN, deep learning, skin tone invariance, gesture recognition, accessibility.},
        month = {July},
        }