Implementation of Embedded Digital Image Processing For Facial Undertone Classification And Hijab Color Recommendation

Nurul Aini Aslan; Ajulio Padly Sembiring; Meryatul Husna

doi:10.30871/jaic.v10i5.13896

Authors

Nurul Aini Aslan Politeknik Negeri Medan
Ajulio Padly Sembiring Politeknik Negeri Medan
Meryatul Husna Politeknik Negeri Medan

DOI:

https://doi.org/10.30871/jaic.v10i5.13896

Keywords:

Computer Vision, Facial Skin Undertone, Hijab Color Recommendation, Image Processing, Raspberry Pi, Region of Interest

Abstract

Selecting a hijab color that harmonizes with facial skin tone is critical for enhancing visual aesthetics and individual confidence. However, color selection in retail stores is conventionally conducted through subjective visual guessing and repetitive physical trials, which leads to operational inefficiencies and color mismatch. This study presents an embedded digital image processing framework deployed on a single-board computer (Raspberry Pi 4) to automate facial skin tone acquisition, undertone classification, and hijab color recommendation in real time. The methodology establishes an end-to-end pipeline comprising image acquisition with a standardized USB webcam, multi-stage Region of Interest (ROI) extraction using automated facial landmarking and forehead/cheek segmentation, illumination compensation via Gray-World white balancing, and quantitative color space transformation. A comparative analysis across RGB, HSV, and CIE L*a*b* spaces was executed, establishing an empirical decision-boundary threshold model based on individual channel distributions (a* and b* chromatic components and R/(G+B) ratios) to categorize skin undertones into Warm, Cool, and Neutral. Testing on 120 diverse demographic datasets across varied illumination conditions (250–650 lux) demonstrated an undertone classification accuracy of 88.33% with an F1-score of 0.88, while user acceptance and expert stylist evaluation yielded an 89.2% satisfaction rate. Running on an embedded Flask architecture, the system maintains a processing latency of 142 ms (18.4 FPS) and low resource utilization. This research provides an objective, reproducible, and computationally efficient edge-computing solution for real-time personalized cosmetic and fashion recommendations.

Downloads

Download data is not yet available.

References

[1]. A. W. Widodo, A. D. Ratnasari, L. Hakim, and S. P. Kristanto, "Design and development of presence system using facial and temperature detections based on Raspberry Pi," Journal of Applied Informatics and Computing, vol. 7, no. 1, pp. 26–33, 2023.

[2]. L. E. Butarbutar, V. F. Tambunan, S. Davina, and H. Syahputra, "Skinmatch: Rekomendasi warna pakaian berdasarkan undertone kulit menggunakan pengolahan citra digital," Journal of Applied Informatics and Computing, vol. 9, no. 2, pp. 391–397, 2025.

[3]. F. W. Prabowo, M. H. Adiya, and R. Kurniawan, "Facial skin color classification using deep convolutional neural networks for cosmetic shade matching," IEEE Access, vol. 12, pp. 186–195, 2024.

[4]. A. D. Putri, S. Adrianto, and D. I. Mulyana, "Hijab color recommendation based on skin tone extraction using optimized K-Nearest Neighbor algorithm," International Journal of Computer Vision and Image Processing, vol. 14, no. 3, pp. 1742–1755, 2025.

[5]. Y. Apridiansyah, E. D. Putra, and A. C. Pratama, "Skin color segmentation using YCbCr color space for robust human face detection," Journal of Computer Science and Information Technology, vol. 19, no. 1, pp. 205–210, 2023.

[6]. R. Helilintar, "Region of interest selection and feature extraction for biometric pattern analysis," Journal of Computing and Informatics Systems, vol. 7, no. 2, pp. 1248–1255, 2023.

[7]. M. P. Chae, S. H. Yoon, and K. B. Kim, "Quantitative skin undertone analysis and personalized cosmetics recommendation using CIE L*a*b* color space," Color Research & Application, vol. 46, no. 5, pp. 1082–1094, 2021.

[8]. H. S. Kim and D. W. Park, "Automated facial skin tone estimation under varying illumination using Gray-World color constancy algorithm," Sensors, vol. 22, no. 14, p. 5241, 2022.

[9]. J. M. Alvarez and C. Lopez, "Illumination-invariant skin detection using normalized chromaticity coordinates and adaptive thresholding," Pattern Recognition Letters, vol. 112, pp. 98–105, 2020.

[10]. R. Wijanarko and N. Eko, "Face detection based on skin color segmentation using YCbCr color space and template matching," Journal of Applied Computer Science and Technology, vol. 4, no. 1, pp. 1–6, 2023.

[11]. S. Saragih, "Implementation of Haar Cascade algorithm using digital image processing for real-time facial attendance system," Journal of Electrical and Informatics Engineering, vol. 5, no. 3, pp. 789–798, 2023.

[12]. A. Rachmaniar, S. Widayati, and K. Rokoyah, "E-commerce product recommendation system using collaborative filtering and content-based filtering," Journal of Information Systems and Informatics, vol. 9, no. 1, pp. 40–54, 2025.

[13]. E. C. Lee and K. R. Park, "Robust facial landmark tracking and feature extraction for embedded smart mirrors," IEEE Transactions on Consumer Electronics, vol. 68, no. 2, pp. 142–151, 2022.

[14]. T. H. Nguyen and S. S. Choi, "Computer vision-based personal color diagnosis framework using skin, hair, and eye spectral properties," Applied Sciences, vol. 11, no. 19, p. 9132, 2021.

[15]. M. Bilal, M. A. Khan, and U. Tariq, "Real-time edge computing on Raspberry Pi 4 for biometric classification: Benchmarks and optimization," Embedded Hardware and Systems Journal, vol. 18, no. 4, pp. 312–324, 2024.

[16]. D. H. F. Gomez, R. F. Santos, and L. M. Silva, "Subjective vs. objective evaluation of virtual makeup and drapery simulation in e-commerce applications," Computers in Industry, vol. 138, p. 103632, 2022.

[17]. P. S. Patel and V. K. Singh, "Comparison of RGB, HSV, and CIE Lab color spaces for human skin tone segmentation under uncontrolled illumination," Multimedia Tools and Applications, vol. 81, no. 10, pp. 14321–14340, 2022.

[18]. Y. Chen, J. Zhang, and X. Liu, "Deep learning-based facial skin tone classification and cosmetic shade matching under dynamic retail lighting," Journal of Imaging Science and Technology, vol. 68, no. 2, pp. 20501–20512, 2024.

[19]. E. C. Charpentier, L. Flament, and S. Diridollou, "A new method for skin color classification based on global CIELAB data and k-means clustering," Color Research & Application, vol. 51, no. 1, pp. 45–58, 2025.

[20]. M. R. Al-Hammadi and S. A. Al-Ghamdi, "Robust human skin tone segmentation and feature extraction using adaptive thresholding in YCbCr and HSV color models," IEEE Access, vol. 11, pp. 102341–102353, 2023.

[21]. K. H. Park and S. Y. Shin, "An automated fashion styling recommendation system considering personal color analysis and garment compatibility," Fashion and Textiles, vol. 10, no. 1, pp. 1–19, 2023.

[22]. V. R. Weir, A. C. Halpern, and K. S. Nehal, "Evaluating skin tone scales for dermatologic and computer vision dataset labeling: Objectivity versus perception," Nature Digital Medicine, vol. 7, no. 1, pp. 112–124, 2024.

[23]. A. Ziqri and N. G. Ramadhan, "Recommendation system based on content-based filtering for retail products," Journal of Software Engineering and Technology, vol. 4, no. 2, pp. 273–278, 2022.