Generative Adversarial Networks (GANs)
GANs are a hot topic in the field of deep learning. They allow to generate new images from noise or perform style transfer between two different images... and even more!
We started to implement an interactive app (Android, iOS), that allows farmers to recognize the illness of plants. The interesting part of this project is the use of library for the voice recognition, based on machine learning methods.
Adidas - Processing and vectorization of hand drawn sketches
Our partnership with Adidas AG is aimed at creating tools to assist fashion designers in their work. We are addressing concerns such as smart processing of pencil sketches, vectorization, pattern recognition of wearable objects.
Project E/R on Landmark Recognition
The project has the aim of studying and implementing algorithms of image processing and pattern recognition for the analysis of large datasets of images and video to identify automatically points, objects and buildings of interest (landmarks) in urban or industrial environment . By comparing the images and videos captured by mobile devices (cameras mounted on vehicles) or from devices such as smartphones and tablets with an image database of places and known or recognizable objects, the system must be able to geo-locate the user (person or vehicle).
Protec - Computer Vision for Sorting
We are creating a Machine Vision application that is able to sort food products detecting anomalies (broken food, wrong sized food, external objects). Our solution improves the sorting quality from previous systems, granting accurate shape analysis of the products (detecting broken food, small or big pieces, twisted or curve objects) and color detection of food's regions (rotten food, external objects).