THE BEST OF ARTIFICIAL

INTELLIGENCE FOR FASHION

From the lab to business, Heuritech was created with one mission in mind: to capture the power of images with cutting-edge visual recognition technology

VIEW DEMO LEARN MORE

THE BEST OF ARTIFICIAL
INTELLIGENCE FOR FASHION

From the lab to business, Heuritech was created with one mission in mind:

to capture the power of images with cutting-edge visual recognition technology

VIEW DEMO LEARN MORE

ARTIFICIAL INTELLIGENCE RESEARCH IS IN OUR DNA

Heuritech was founded by PhDs in Artificial Intelligence

and has grown through continuous R&D since six years.

Precision, accuracy, and expertise are in our DNA.

READ OUR TECH BLOG

WHAT IS ARTIFICIAL INTELLIGENCE ?

We define Artificial Intelligence as intelligent programs that achieve tasks usually tackled by humans. The specific domain we focus on is deep learning, a breakthrough that has been revolutionizing artificial intelligence since 2010. Thanks to deep learning, the machine can autonomously learn to recognize concepts that make sense for us humans, such as a landscapes, handbags, a smiling face, etc. We apply deep learning techniques to image recognition.

READ OUR AI DICTIONARY

35%

of PhDs in Artificial Intelligence

scientific papers published
at international conferences

95%

precision of our models

3 Years

of historical data

A STATE OF THE ART ARTIFICIAL INTELLIGENCE FOR IMAGES

Our industry-leading visual recognition technology accurately analyzes 3 million images everyday

Visual recognition technology, also called computer vision or image recognition, focuses on analyzing images. It means that a model can recognize specific items in pictures – such as clothes in Heuritech’s case. We have created our own proprietary Deep Neural Network (DNN) architecture, training algorithms and active learning systems. Our models can recognize a new fashion item in one day.

More than 2000 fashion details are recognized in any image, from a specific model to general trends. Some examples of what our model can recognize are styles, colors, patterns, materials, environments, textures, products, shapes, etc. We focus on minute details to make a difference, e.g. being able to recognize asymmetrical, satin, scarlet, etc.

READ OUR RESEARCH PAPERS

DELIVERING ACCURATE INSIGHT FROM THE BEST DATA

Heuritech has created in-house its own data collection and advanced analysis thanks to a dedicated team of data scientists.

The data we collect are from social media (Instagram, Weibo, blogs), partnerships (e-commerce websites, in-store historical sales data, Google Search) and fashion expertise (Fashion Shows, Getty images, influencers).

We spot fashion trends by their product type and best associated features (colors, patterns, textures or shapes) based on what appears on the catwalk as well as in the streets.

To understand the fashion trends of tomorrow, we developed and validated algorithms that forecast the propagation of trends on social media and capture their adoption in different market segments.