A Deep Learning Framework for Personalized Fashion Recommendations Based on Skin Tone Analysis

Abstract—The personalization of virtual fashion recommendations remains hindered by limited integration of chromatic and anthropometric factors, especially skin tone compatibility. This study addresses a critical research gap by proposing a voice-enabled 3D fashion recommendation system that incorporates deep learning-based skin tone classification and adaptive garment suggestion. The primary objective is to enhance aesthetic compatibility and user satisfaction through real-time, personalized recommendations. Utilizing a custom-designed Deep Convolutional Neural Network (DCNN) and reinforcement learning algorithms, the system classifies user skin tones with 89.14% accuracy and adapts recommendations based on user feedback, reducing outfit resets by 54%. A curated dataset encompassing five skin tone categories and a multi-stage image preprocessing pipeline ensures inclusive and robust performance. The results demonstrate significant improvements in recommendation relevance and user engagement, with 88% satisfaction and 93.7% dominant tone detection accuracy. These findings underscore the system's potential to set new benchmarks in personalized fashion retail while promoting inclusivity and sustainable consumer practices.

Skin Tone Classification, Personalized Fashion Recommendation, Reinforcement Learning, 3D Virtual Try-on, Deep Convolutional Neural Network (DCNN)

1. S. Huang and L. Huang, ‘CLO3D-Based 3D Virtual Fitting Technology of Down Jacket and Simulation Research on Dynamic Effect of Cloth’, Wirel. Commun. Mob. Comput., vol. 2022, pp. 1–11, Feb. 2022, doi: 10.1155/2022/5835026. [Google Scholar] [Crossref]

2. M. Sekine, K. Sugita, F. Perbet, B. Stenger, and M. Nishiyama, ‘Virtual Fitting by Single-Shot Body Shape Estimation’, in Proceedings of the 5th International Conference on 3D Body Scanning Technologies, Lugano, Switzerland, 21-22 October 2014, Lugano, Switzerland: Hometrica Consulting - Dr. Nicola D’Apuzzo, Oct. 2014, pp. 406–413. doi: 10.15221/14.406. [Google Scholar] [Crossref]

3. S. Wazarkar et al., ‘Advanced Fashion Recommendation System for Different Body Types using Deep Learning Models’, In Review, preprint,Jul. 2022. doi: 10.21203/rs.3.rs-1856954/v1. [Google Scholar] [Crossref]

4. Y. Deldjoo et al., ‘A Review of Modern Fashion Recommender Systems’, 2022, doi: 10.48550/ARXIV.2202.02757. [Google Scholar] [Crossref]

5. M. Dong, X. Zeng, L. Koehl, and J. Zhang, ‘An interactive knowledge-based recommender system for fashion product design in the big data environment’, Inf. Sci., vol. 540, pp. 469–488, Nov. 2020, doi: 10.1016/j.ins.2020.05.094. [Google Scholar] [Crossref]

6. H. Fathi, A. R. Ahmadyfard, and H. Khosravi, ‘Deformable 3D Shape Matching to Try on Virtual Clothes via Laplacian-Beltrami Descriptor’, J. AI Data Min., vol. 10, no. 1, Jan. 2022, doi: 10.22044/jadm.2021.10749.2212. [Google Scholar] [Crossref]

7. M. F. Hashmi, B. K. K. Ashish, A. G. Keskar, N. D. Bokde, and Z. W. Geem, ‘FashionFit: Analysis of Mapping 3D Pose and Neural Body Fit for Custom Virtual Try-On’, IEEE Access, vol. 8, pp. 91603–91615, 2020, doi: 10.1109/ACCESS.2020.2993574. [Google Scholar] [Crossref]

8. Papazoglou Chalikias et al., ‘Novel Paradigms of Human-Fashion Interaction’, in Proceedings of the 12th Hellenic Conference on Artificial Intelligence, Corfu Greece: ACM, Sep. 2022, pp. 1–11. doi: 10.1145/3549737.3549803. [Google Scholar] [Crossref]

9. M. Sridevi, N. ManikyaArun, M. Sheshikala, and E. Sudarshan, ‘Personalized fashion recommender system with image based neural networks’, IOP Conf. Ser. Mater. Sci. Eng., vol. 981, p. 022073, Dec. 2020, doi: 10.1088/1757-899X/981/2/022073. [Google Scholar] [Crossref]

10. M. Wang, J. Marsden, and B. Thomas, ‘Smart mirror fashion technology for better customer brand engagement’, Int. J. Fash. Des. Technol. Educ., pp. 1–12, Aug. 2023, doi: 10.1080/17543266.2023.2243485. [Google Scholar] [Crossref]

11. D. Werdayani and I. Widiaty, ‘Virtual fitting room technology in fashion design’, IOP Conf. Ser. Mater. Sci. Eng., vol. 1098, no. 2, p. 022110, Mar. 2021, doi: 10.1088/1757- 899X/1098/2/022110. [Google Scholar] [Crossref]

12. Manukalpa, J. C. S., & Dissanayake, H. P. (2025). Empowering Communication for Paralyzed Individuals and Spinal Cord Injury Patients: An Intelligent System With Eye Gaze Tracking, Voice Assistance, and Chat-Bot Integration. International Journal of Latest Technology in Engineering, Management & Applied Science, 14(3), 81-89. [Google Scholar] [Crossref]

13. Jayawardena, A., Manukalpa, C. S., Bopage, H., Panduwawala, P., Pulasinghe, K., & Rajapakshe, S. (2024, December). A Multimodal Interaction System for Speech-Based Autism Intervention in Sinhala-Speaking Sri Lankan Children using the NAO Robot. In 2024 6th International Conference on Advancements in Computing (ICAC) (pp. 205-210). IEEE. [Google Scholar] [Crossref]

14. Manukalpa, C. S., Pulasinghe, K., & Rajapakshe, S. (2025, April). Designing Culturally Adaptive Emotional Gestures to Enhance Child-Robot Interaction with NAO Robots in ASD Therapy. In 2025 International Research Conference on Smart Computing and Systems Engineering (SCSE) (pp. 1-6). IEEE. [Google Scholar] [Crossref]

15. Sri, J. C. An Integrative Approach to Weather Analysis and Disaster Preparedness for 25 Districts in Sri Lanka: A Data Warehousing Perspective. [Google Scholar] [Crossref]

• Most Advanced Construction Material for Typical Boilers
• Nutrigenetic Impact of PEMT Gene Polymorphism Rs7946 On Choline Metabolism and Its Role in Personalised Nutrition
• Evaluating the Influence Factors of Media on Investor Sentiment Towards Stock Market Investments.
• To Compare the Effectiveness of Manual Traction and Mechanical Traction in Patient with Cervicogenic Headache
• Is Green Human Resource Management the Newest Trend or A Strategic Necessity?