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{196948,
        author = {Dhairya Dayanand Bandekar and Bhavika Atul Patil and Priyanshu Anil Kumar Yadav and Sonal Kadam},
        title = {DermaClust: A Multimodal, Severity-Calibrated Neural Paradigm for Skin Morphological Disparity Modeling and Cross-Domain Product Vector Synthesis via Biometric-Gated Access},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {6304-6314},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=196948},
        abstract = {Numerous skincare selections are influenced by assumptions, personal opinions, and advertising claims, which can lead to unsuitable product choices and recurring skin issues. This study presents DermaClust, a multimodal intelligent framework designed to create personalized skincare recommendations. The system integrates transformer-based ingredient understanding, deep learning driven visual skin analysis, and environmental context awareness. It employs weighted hybrid profiling, climate aware scoring, and localized skin patch evaluation to generate objective and reliable recommendations. The proposed approach demonstrates how the integration of computer vision and natural language processing can support safer and evidence based cosmetic decision making.},
        keywords = {Transformer models, deep learning, computer vision, skin analysis, personalized recommendation, multimodal artificial intelligence, skincare intelligence.},
        month = {April},
        }