This repository contains all experiments conducted part of my undergraduate thesis titled "Applications of Artificial Intelligence in Fashion Industry" at OUTR.
Artificial Intelligence has significantly influenced every aspect of the fashion industry, spanning design, production, and consumption. With its rapid pace of development, AI has seamlessly integrated into the fashion world, known for its openness to adopting new technologies. Over the past decade, AI has been utilized for analyzing fashion trends and understanding consumer preferences. Its impact on style and its role in phenomena like Fast Fashion is undeniable. The digitalization of the clothing industry, evolving from version 4.0 to an imminent 5.0, underscores the increasing reliance on advanced technology, particularly the broader integration of Artificial Intelligence. This involves diverse applications such as Recommendation Systems, Anomaly Detection in Textiles, Smart Textiles, AI-based Designing, Trend Prediction, and more.
Using Generative Adversarial Networks, GuccioAI can generate clothing images and mix these images. While mixing, you can control which structure or style that you want the clothing to copy. Additionally, you can edit the generated clothing with several given attributes such as dark colour, jacket, dress, or coat.
Using Neural Nets, iDresser unlike the conventional systems that rely on the user's previous purchases and history, this project aims at using an image of a product given as input by the user to generate recommendations since many-a-time people see something that they are interested in and tend to look for products that are similar to that.
The system uses pixel-wise detection algorthims to detect various product categories in the user input image and then segments it to particular types of clothing like Tshirts, Pants, Jackets etc and further can be used to find similar products based on a certain kind of segementation.
A recommender system that recommends the clothes to the female customers for their rental purpose. The rental purposes depend on the activities a user wants to carry out, such as: vacation, meetings, weddings, dates, etc. The recommendation is based on the features like customers’ height, weight, bust size, body type, age, and reason to rent.This improves costumer's experience and preserves trend in fashion.
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent