iDECOR: AI-powered Furniture Detector & Recommender to provide recommendations for most similar furniture items to users' input.

Data Science & Machine Learning Immersive

Cohort 10

Project description

iDECOR is a customized solution for furniture shoppers by wrapping furniture detection and recommendation system into a single, seamless process on Streamlit. This product leverages two deep learning technologies - 1) Detectron2 developed by Facebook to detect every possible furniture item in the user's uploaded image, and 2) VGG16 model to help narrow down most similar items to the detected item in terms of visual cues, and return them with top 5 items from our furniture product catalogue, in order to drive conversions to sales of furniture retailers by improving onsite recommendations. iDECOR is made available across 6 furniture products as the first step, and will expand to more brands/categories with API support in the future.