By Kornel Kiss - 24.02.2020 - Company
We 💓 technology. But we only believe in using the latest innovations when it will improve the way we work or the product we offer. Computer vision is an AI-based technology that recognises and labels images. We’re using it to automatically identify drivers who are taking our training.
Before the training starts, students have to take a picture of their driving licences, as well as a selfie, for the system to then be able to identify that person.
We live in a world that is obsessed with image. Whether it’s sharing pictures of food and exotic holiday locations on Instagram, sharing selfies with friends on Snapchat or reviewing controversial referring decisions in rugby and football, we’re becoming increasingly focused on visuals. But how do we catalogue and make sense of this growing number of images?
Computer vision (CV) automates a manual human task – that of “seeing” what is in photos, understanding context, and being able to pick out important objects. Have you ever signed into an account and been asked to pick out all the squares of an image that have traffic lights in them? This is the equivalent of computer vision.
You need to know who is carrying out your training and how much time they are spending on it. ANET’s digitalised driver identification solution uses computer vision to automatically identify drivers who are taking your training. Before the training starts, students have to take a picture of their driving licences, as well as a selfie, for the system to then be able to identify that person.
We’ve also added an extra layer of protection: training administrators and people with access to our admin page have to manually approve the pictures to make sure the system works properly. The system will then record the date, time and name of the person who approved the pictures. Trainers and training providers can see exactly what drivers do or don't do, whether they are carrying out the training remotely at home or in the office.