in Case studies
Client: Teezily
Automated image quality detection engine for retail
Case study details
Teezily, the French-based but globally operating eCommerce company with a unique business model, was looking for an AI solution to improve its performance by automating processes.
Addepto Team delivered the computer vision engine for image detection, and proved itself to be a reliable partner in implementing customized AI models into existing eCommerce infrastructure.
Challenge
Uploading the artwork to the platform
Approach
Detect and evaluate the quality of images with the use of state-of-the-art computer vision algorithms – VGG.
Goal
Implement an automated AI tool to assess the technical quality of the images.
Outcome
A working software ready-to-integrate with the eCommerce backend platform.
Challenge
Teezily's business model - although looks relatively straightforward and appealing - turned out to be challenging in practice.
Teezily’s is an eCommerce platform that enables designers to create and sell their own clothing line while taking care of the business aspects such as production, promotion, and logistics, saying, “You have the ideas. We’re the platform. No cost, no worries; it’s easy with Teezily!”
Business model
Problems appeared when it occurred that the unleashed users’ creativity needed to be taken under some control in the name of quality improvement of end-products.
The assumption was clear: users upload their artwork to the platform and choose the items that are aimed to be produced, like t-shirts, and that’s it.
Uploading the artwork to the platform
Teezily serves as a factory responsible for transforming ideas into a specific product, selling them, and delivering them to end clients.
And yet, the very first step – uploading the artwork to the platform – was problematic, as the quality of images sometimes needed to meet the desired standards. They happened to be blurred, poorly cropped, or otherwise distorted, making it difficult to print them on T-shirts.
Approach
Images quality assessment.
The solution developed by Addepto was supposed to detect and evaluate the quality of images. The outcome met Teezily’s expectations, so it was transformed into a working software ready-to-integrate with the eCommerce backend platform.
During project development, our team worked on:
- Effectively detecting and evaluating the quality of images. The solution was based on - then - state-of-the-art computer vision algorithms - VGG.
- Building an advanced solution to meet Teezily's needs. It was equipped with several upfront quality control rules and trained on images uploaded to the platform to perform the controlling processes.
Goal
Implementation of automated AI tool
Teezily was focused on enhancing the caliber of products available to customers.
Increasing the staff to conduct manual checks of uploaded images was not feasible due to the cost, time consumption, and clash with the company's primary concept of allowing people to express themselves creatively.
With no internal AI division, the sole solution was to use an automated AI tool to assess the technical quality of the images. Though they needed to gain expertise in this area, the team was conscious of the complexities associated with this technology.
Let's discuss
a solution
for you
Edwin Lisowski
will help you estimate
your project.
- hi@addepto.com
Other case studies
Testing life cycles in manufacturing aerospace
Woodward is an independent designer, manufacturer, and service provider of energy control and optimization solutions for aerospace and industrial markets. The company was founded over 150 years ago. It was focused on delivering proven syste...
Compliance analysis at Retail
Spencer’s is a North American mall retailer with over 600 stores in the United States and Canada. Their stores offer gag gifts, clothing, band merchandise, sex toys, room decor, collectible figures, fashion and body jewelry, and fanta...