AI-Based Outfit Rating and Suggestion System

Notice

This is an unedited manuscript accepted for publication and provided as an Article in Press for early access at the author’s request. The article will undergo copyediting, typesetting, and galley proof review before final publication. Please be aware that errors may be identified during production that could affect the content. All legal disclaimers of the journal apply.

Year : 2026 | Volume : 13 | 02 | Page :
    By

    Sneha Vivek Pandey,

  • Pranali Parate,

  • Shweta Waghmare,

  1. Research Scholar, Department of MCA, Thakur Institute of Management Studies, Career Development & Research (TIMSCDR) Mumbai, Maharashtra, India
  2. Research Scholar, Department of MCA, Thakur Institute of Management Studies, Career Development & Research (TIMSCDR) Mumbai, Maharashtra, India
  3. Assistant Professor, Department of MCA, Thakur Institute of Management Studies, Career Development & Research (TIMSCDR) Mumbai, Maharashtra, India

Abstract

The increasing demand for personalised fashion advice in the digital era has highlighted the need for intelligent, automated styling solutions. The AI-Based Outfit Rating and Suggestion System is a web- based platform that assists users in evaluating and improving their clothing choices through intelligent image analysis. Unlike conventional fashion applications that merely identify garment categories or suggest purchases, this system performs a holistic assessment of complete outfits by analysing colour coordination, pattern matching, garment compatibility, and accessory usage. The system leverages Computer Vision techniques, including YOLOv5 and ResNet-based models, for accurate clothing detection and feature extraction. Natural Language Processing (NLP) is then employed to translate the quantitative analysis into clear, actionable, human-readable feedback that guides users in enhancing their personal style. Each outfit is assigned a numerical score on a scale of 0 to 10, accompanied by a detailed explanation of the rating and specific improvement suggestions such as colour substitutions, accessory additions, or pattern adjustments. The backend is developed using Java Spring Boot, which handles all core operations including AI model execution, database interaction, and user authentication. User data, outfit history, and analysis results are stored securely in MongoDB. BCrypt encryption and JWT-based authentication are implemented to safeguard user information against unauthorised access. The frontend is built with React.js and Tailwind CSS, presenting a responsive dark-themed interface accessible on both desktop and mobile platforms. Evaluation results show a mean rating precision of 8.2/10, an 87% colour harmony alignment with human stylist judgements, and a pattern coordination success rate of 82%. Furthermore, 90% of users found the system’s suggestions actionable, and 75% reported greater confidence in their outfit choices. This system demonstrates the potential of AI to deliver intelligent, explainable, and personalised fashion guidance for everyday use.

Keywords: AI-based outfit rating, computer vision, clothing detection, natural language processing, machine learning, personalised fashion, JWT authentication, Java Spring Boot, React.js, style rating, outfit suggestion system

How to cite this article:
Sneha Vivek Pandey, Pranali Parate, Shweta Waghmare. AI-Based Outfit Rating and Suggestion System. Journal of Image Processing & Pattern Recognition Progress. 2026; 13(02):-.
How to cite this URL:
Sneha Vivek Pandey, Pranali Parate, Shweta Waghmare. AI-Based Outfit Rating and Suggestion System. Journal of Image Processing & Pattern Recognition Progress. 2026; 13(02):-. Available from: https://journals.stmjournals.com/joipprp/article=2026/view=247696


References

  1. Mustaffa MR, Feng OS, Norowi NM, Hussin M. Outfit classification and recommendation based on integrated features and bagged decision tree. Int J Adv Res Eng Technol. 2020;11(12):1400-1409.
  2. A K, Kumar PVR, Nagula SU, Nagelli A. Fashion recommendation system. Int J Res Appl Sci Eng Technol. 2023;11.
  3. Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. Commun ACM. 2017;60:84-90.
  4. Anjan M, Abhishek V, Dheeraj D, Veenugeetha Y. Fashion recommendation system using CNN. Int J Adv Res Ideas Innov Technol. 2020;6(2):780-783.
  5. Liu Z, Song G, Liu G, et al. Street-to-shop: Cross-scenario clothing retrieval via parts alignment and auxiliary set. In: Proc IEEE Conf Comput Vis Pattern Recognit (CVPR); 2012; Providence, RI, USA. Piscataway (NJ): IEEE; 2012. p. 3330-3337.
  6. Liu J, Shi Y. Image feature extraction method based on shape characteristics and its application in medical image analysis. In: Proc Int Conf Appl Inform Commun; 2011 Aug; Xi’an, China. Cham: Springer; 2011. p. 172-178.
  7. Gülbaş B, Şengür A, İncel E, Akbulut Y. Deep features and extreme learning machines-based apparel classification. In: Proc Int Artif Intell Data Process Symp (IDAP); 2019 Sep; Malatya, Turkey. Piscataway (NJ): IEEE; 2019. p. 1-4.
  8. Wang N, Ai H. Who blocks who: Simultaneous clothing segmentation for grouping images. In: Proc IEEE Int Conf Comput Vis (ICCV); 2011; Barcelona, Spain. Piscataway (NJ): IEEE; 2011. p. 1535-1542.
  9. Chakraborty S, Hoque MS, Surid SM. A comprehensive review on image based style prediction and online fashion recommendation. J Mod Technol Eng. 2020;5(3):212-233.
  10. Park J, Ciampaglia GL, Ferrara E. Style in the age of Instagram: Predicting success within the fashion industry using social media. In: Proc 19th ACM Conf Comput Support Coop Work Soc Comput (CSCW); 2016 Feb-Mar; San Francisco, CA, USA. New York (NY): ACM; 2016. p. 64-73.
  11. Spiller L, Tuten T. Integrating metrics across the marketing curriculum: The digital and social media opportunity. J Mark Educ. 2015;37(2):114-126.
  12. Wu M, Goodman N. Multimodal generative models for scalable weakly-supervised learning. Adv Neural Inf Process Syst. 2018;31:5575-5585.
  13. Mao X, Li Q, Xie H, Lau RYK, Wang Z, Smolley SP. Least squares generative adversarial networks. In: Proc IEEE Int Conf Comput Vis (ICCV); 2017; Venice, Italy. Piscataway (NJ): IEEE; 2017. p. 2794-2802.
  14. Isola P, Zhu JY, Zhou T, Efros AA. Image-to-image translation with conditional adversarial networks. In: Proc IEEE Conf Comput Vis Pattern Recognit (CVPR); 2017; Honolulu, HI, USA. Piscataway (NJ): IEEE; 2017. p. 1125-1134.
  15. Choi Y, Choi M, Kim M, Ha JW, Kim S, Choo J. StarGAN: Unified generative adversarial networks for multi-domain image-to-image translation. In: Proc IEEE Conf Comput Vis Pattern Recognit (CVPR); 2018; Salt Lake City, UT, USA. Piscataway (NJ): IEEE; 2018. p. 8789-8797.
  16. Lee HY, Tseng HY, Huang JB, Singh M, Yang MH. Diverse image-to-image translation via disentangled representations. In: Proc Eur Conf Comput Vis (ECCV); 2018; Munich, Germany. Cham: Springer; 2018. p. 35-51.
  17. Gu S, Liu X, Cai L, Shen J. Fashion coordinates recommendation based on user behavior and visual clothing style. In: Proc 3rd Int Conf Commun Inf Process; 2017; Tokyo, Japan. New York (NY): ACM; 2017. p. 185-189.
  18. Gu X, Wong Y, Peng P, Shou L, Chen G, Kankanhalli MS. Understanding fashion trends from street photos via neighbour-constrained embedding learning. In: Proc 25th ACM Int Conf Multimed; 2017; Mountain View, CA, USA. New York (NY): ACM; 2017. p. 190-198.
  19. He R, Lin C, McAuley J. Fashionista: A fashion-aware graphical system for exploring visually similar items. In: Proc 25th Int World Wide Web Conf Companion; 2016; Montreal, Canada. New York (NY): ACM; 2016. p. 199-202.
  20. Xian W, Sangkloy P, Agrawal V, et al. TextureGAN: Controlling deep image synthesis with texture patches. In: Proc IEEE Conf Comput Vis Pattern Recognit (CVPR); 2018; Salt Lake City, UT, USA. Piscataway (NJ): IEEE; 2018. p. 8456-8465.
  21. He T, Hu Y. FashionNet: Personalized outfit recommendation with deep neural network. arXiv [Preprint]. 2018. Available from: arXiv:1810.02443.
  22. Gorripati KS, Angadi A. Visual based fashion clothes recommendation with convolutional neural networks. Int J Inf Syst Manag Sci. 2018;1(1).
Ahead of Print Subscription Original Research
Volume 13
02
Received 10/03/2026
Accepted 20/06/2026
Published 26/06/2026
Publication Time 108 Days
29

Login


My IP

PlumX Metrics