International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | Real-Time Emotion Recognition with AI-Based Artistic Synthesis |
|---|---|
| ABSTRACT | Facial emotion recognition is a key application of Artificial Intelligence (AI) and Computer Vision, enabling machines to interpret human emotional states from facial expressions. This project, titled “Real-Time Emotion Recognition with AI-Based Artistic Synthesis,” combines emotion detection with creative art generation. Using the BEiT Vision Transformer model, facial images are resized to 224×224 pixels and classified into seven emotions: Angry, Disgust, Fear, Happy, Neutral, Sad, and Surprise. A softmax function calculates probability scores, and the dominant emotion is selected. Unlike traditional systems that stop at classification, this project integrates Generative AI to create expressive artwork. A descriptive artistic prompt is generated and passed to the Stable Diffusion XL model via Hugging Face’s API, producing unique art that reflects the emotional state.This integration introduces a human-centered AI application that makes technology more interactive and empathetic. Transformer-based architectures ensure robust performance in real-time emotion recognition, while generative models add creativity. The novelty lies in extending emotion detection beyond analytics, offering machines the ability to engage with human emotions in expressive ways. It highlights AI not only as a tool for analysis but also as a medium for artistic interpretation. This approach bridges perception and creativity.The applications are diverse and impactful, spanning digital therapy, where emotions can be visualized for patient support, creative media design, enabling emotion-driven storytelling, and interactive entertainment, enhancing immersive experiences. It also contributes to human-computer interaction, making machines more empathetic and engaging. By merging deep learning with generative AI, this project shows how technology can evolve into systems that are both intelligent and expressive. It paves the way for innovative, emotion-driven computing solutions. |
| AUTHOR | T. SUJATHA, Y.GAYATRI, K. YAMINI DEVIKA, B.PALLAVI DURGA, P. SARIKA, B.ARAVIND, R.PRADEEP CHANDU Assistant Professor, Department of CSE (Data Science), NSRIT, Vishakhapatnam, India Student of Department of CSE (Data Science), NSRIT, Vishakhapatnam, India |
| VOLUME | 182 |
| DOI | DOI: 10.15680/IJIRCCE. 2026.1403100 |
| pdf/100_Real-Time Emotion Recognition with AI-Based Artistic Synthesis.pdf | |
| KEYWORDS | |
| References | 1. Li, S.; Deng, W. Deep Facial Expression Recognition: A Survey. IEEE Transactions on Affective Computing 2020, 13(3), 1195–1215. [Crossref] 2. Dosovitskiy, A.; Beyer, L.; Kolesnikov, A.; et al. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. arXiv 2020, arXiv:2010.11929. [Crossref] 3. Bao, H.; Dong, L.; Wei, F. BEiT: BERT Pre-Training of Image Transformers. arXiv 2021, arXiv:2106.08254. [Crossref] 4. Kaur, P.; Singh, P.; Kumar, H. Emotion Recognition from Facial Expressions using Deep Learning. Procedia Computer Science 2021, 189, 72–79. [Crossref] 5. Zhang, Z.; Luo, P.; Loy, C.C.; Tang, X. Learning Social Relation Traits from Face Images. ICCV 2015, pp. 3631–3639. [Crossref] 6. Rombach, R.; Blattmann, A.; Lorenz, D.; Esser, P.; Ommer, B. High-Resolution Image Synthesis with Latent Diffusion Models. CVPR 2022, pp. 10684–10695. [Crossref] 7. Poddar, S.; Saha, S.; Dutta, A. Real-Time Facial Emotion Recognition using Vision Transformers. IEEE Access 2023, 11, 45678–45690. [Crossref] 8. Wang, H.; Li, Y.; Zhang, J. Emotion-Driven Generative Art using AI: A Novel Framework for Human-Computer Interaction. Journal of Visual Communication and Image Representation 2023, 90, 103741. [Crossref] |
