Image-Based Recommender System

Business Use case

This solution helps e-commerce companies recommend visually and contextuallysimilar
items to help boost revenue. Example user flow is: let’s say you like a t-shirtwhile surfing on
Instagram. You take a screenshot, and upload this picture tothis service. The web app
recommends visually similar t-shirts from the prefilleddatabase that is connected to the
database of fashion brands. On purchase fromthe web app, it gets a 5% cut from the
fashion brand.

Client

a. Marketing Firm in Münich, Germany with 20 – 50 employees.

b. Digital Transformation firm in Sydney, Australia with 20 – 50 employees.

C. Currently in the pre-production phase. Will be deployed to production soon.

Use cases solves

1. Object Detection: Detection of 2000 different types of common objects.
2. Image Segmentation: Detect and mask background clutter for accurate objectdetection.
3. Image Matching: Compute image similarity and performing image clustering toperform accurate image retrieval.

Technologies Used

Python, C/C++, Django, OpenCV, Scikit-learn,

‍