The MTM online solution that uses Computer Vision,
3D Matching, and Machine Learning to take the
most accurate human body measurements on the market
Computer vision is used to evaluate the photos from which we obtain and process the human body measurements. Our advanced CV algorithms allow us to accurately recognize and identify the human body on photos that were taken with any mobile device on any background environment.
Every human body contains biometric information and we are using this characteristic for a highly precise matching that leads to an accurate measurement estimate. This optical methodology allows us to obtain the most accurate human body measurements on the market.
Neural networks are used to detect and determine key points and generate a set of probability maps for each key point. Our neural networks are trained with fully measured human body images with pre-arranged key points based on our handmade human body measurements solid database. These dozens measurements help us detect specific patterns in images and will define the unique characteristics of each body size and shape.