International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 12 Issue: 10 | Oct 2025
p-ISSN: 2395-0072
www.irjet.net
Skin Tone Based Product (Dress) Recommendation Using Deep Learning and Content-Based Filtering R Savitha, K S Udhayarani, R Sindhiya R Savitha Dept. of CSE, K.L.N College of Engineering, Tamil Nadu, India K S Udhayarani Dept. of CSE, K.L.N College of Engineering, Tamil Nadu, India R Sindhiya Assistant Professor Dept. of CSE, K.L.N College of Engineering, Tamil Nadu, India ---------------------------------------------------------------------***--------------------------------------------------------------------1.1 Problem Statement Abstract - The advancement of Artificial Intelligence and Computer Vision has enabled intelligent systems to assist users in personalized product selection. This paper presents a Skin Tone Based Product (Dress) Recommendation System using Deep Learning and Content-Based Filtering techniques. The proposed system automatically detects a user’s skin tone (classified as light, mid-light, mid-dark, or dark) using Convolutional Neural Networks (CNN). Based on the identified skin tone, the system recommends suitable dress colors for both men and women—Sarees and Chudidhar for women, and Shirts and Pants for men. The deep learning model is trained with diverse datasets of human faces to ensure accurate tone detection, while content-based filtering utilizes pre-defined color–tone relationships to generate recommendations. This approach helps users choose outfits that complement their natural skin tone, enhancing both appearance and confidence. The system is implemented using Python, TensorFlow, and Flask, providing a user-friendly web interface that captures an image, predicts tone, and displays the recommended product set. The project demonstrates the integration of machine learning and recommendation systems to create intelligent, personalized fashion assistance tools.
In today’s fashion and online shopping environment, customers often face difficulty in choosing dress colors that complement their unique skin tones. Many individuals, especially those shopping online, end up selecting colors that may not suit their complexion, leading to dissatisfaction and reduced confidence in appearance. Traditional e-commerce platforms recommend products based on popularity or user ratings, without considering the user’s physical attributes such as skin tone. This gap highlights the need for an intelligent recommendation system that can analyze a user’s skin tone and suggest the most suitable dress colors. Therefore, there is a strong demand for a personalized system that enhances user satisfaction by recommending color-appropriate dresses such as sarees, chudidhar, shirts, and pants based on the detected skin tone categories like light, mid-light, mid-dark, and dark.:
1.2 Objectives of the Study The main objective of this study is to design and develop an intelligent dress recommendation system that suggests suitable outfit colours based on a user’s skin tone using Deep Learning and Content-Based Filtering techniques. The system automatically detects the user’s skin tone from an uploaded or real-time captured image and classifies it into one of the predefined tone categories such as dark, light, mid-dark, mid-light.
Key Words: Skin tone detection, Deep learning, CNN, Content-based filtering, Dress recommendation, Personalized fashion, Computer vision, Python.
1.INTRODUCTION With the increasing influence of artificial intelligence in the fashion industry, personalized product recommendations have become highly desirable. Many users face difficulty choosing outfits that complement their unique skin tone. The Skin Tone Based Product (Dress) Recommendation System aims to solve this challenge by analysing a person’s facial image to detect their skin tone and suggest suitable dress colours accordingly. The system employs Deep Learning (CNN) for accurate skin tone classification and Content-Based Filtering for generating recommendations.
Based on the detected skin tone, the system recommends colour-appropriate dresses—sarees and chudidhars for women, and shirts and pants for men—that best complement the user’s complexion. The platform also allows users to either capture their image in real time using a webcam or upload an existing photo, giving flexibility and control over how they interact with the system.
2LITERATURE REVIEW The literature review provides insights into the existing research and technological developments related to product recommendation systems, deep learning models, and content-based filtering techniques. Several studies have focused on personalized recommendation systems that analyse user preferences, purchase history, or behaviour
The proposed model enhances the shopping experience by providing intelligent and personalized suggestions, thereby bridging the gap between technology and fashion. .
© 2025, IRJET
|
Impact Factor value: 8.315
|
ISO 9001:2008 Certified Journal
|
Page 557