We support your company in accessing novel solutions based on the most recent advances in Artificial Intelligence
and Deep Learning
Our expertise is in Machine Learning with applications in Computer Vision and Natural Language Processing
From prototypes to scalable solutions
Solutions on the cloud and on edge devices
Optimized workflows for increased speed and performance
At Quaesta AI we like the challenging problems, let's get in touch to see how AI can impact on your business
Contact Us
We are engineers with a solid background in scientific research in AI, and innovative problem solving is one of our biggest strengths: at Quaesta AI we strive to design solutions able to bring impactful technological advances to your products
We highly value the usability of our products, that is why we carefully develop intuitive, simple and yet rich interfaces able to disclosure complexity progressively based on needs
We know how crucial it may be for your company to understand why a model has made a certain decision, that is why we strive to provide you tools aimed for a better understanding of the decision making process behind our models
Possibility of integration
of our runtime libraries in your favorite platform:
Logos are registered trademark
Robust models in the presence of characters with deformations, occlusions, and blurred images
learn more
Detect position and orientation of objects in images, train models with few images per class
learn more
Detect anomalies in regular surfaces with regular patterns, such as cracks, defects, discoloration, also when they are unknown a priori
learn more
Mark with pixel granularity the areas of the image belonging to one or more classes, as well as different instances of the classes considered
Our classifiers only need few (10-50) labelled images per class
Robust out-of-the-box models recognizing characters in presence of deformations, partial occlusions, noisy and blurred images
Stunning accuracy also with non-standards fonts and reflective surfaces, where traditional OCR fails
Optical Character Verification (OCV) based on user-defined patterns
Possibility to refine the model online with annotated images for brilliant performances on the most difficult OCR scenarios
Pre-trained out-of-the-box models for generic object detection capable of identifying position and orientation of more than 600 objects in an image
Robust models recognizing objects in the presence of rotations, deformations and partial occlusions
Customized models trained using ad-hoc synthetic datasets for domain-specific object detection with superior performances on the most challenging tasks
Zero-shot object detection allows to detect images of objects never
seen in training
Pre-trained out-of-the-box models capable of identifying anomalies in regular surfaces with regular patterns, such as cracks, defects, discoloration
Customized models trained with only few images of flawless cases can successfully identify anomalous examples of unlikely appearance in images coming from specific domains
Anomalous samples can be provided to the model to better discriminate anomalies and tune the sensitivity and determine the acceptable sample variability
Anomalies are highlighted in the image with heatmaps to highlight missing or extra elements and support model explainability
Images taken from the MVTEC AD dataset (https://www.mvtec.com/company/research/datasets/mvtec-ad), heatmaps generated by algorithms developed by Quaesta AI
Due to privacy reasons, not all our clients are mentioned in this section
"Quaesta AI provided us with the ability to perform Deep Learning-based OCR on noisy images with distorted characters on curved surfaces, where the tools we used based on standard OCR previously failed. Thanks to the OCR library by Quaesta AI, at Studio Progetti Automation we have increased the performance of our control systems, being able to guarantee high quality inspection standards. This allowed us to increase the technical offer towards our clients, who are more demanding than ever in terms of standards of quality control."
Ing. Alessandro Antonelli, Partner
PhD in Information Technology with 15+ years of research experience in Machine Learning and Stochastic Optimization
PhD in Theoretical and Computational Physics, researcher in Machine Learning with 10+ years of experience
Final year PhD Student in Computer Science with 4+ years in Machine Learning Research and 3+ as Software Engineer
4+ years in Software Development. BS in Automation and Computer Science. External collaborator
15+ years in management, legal, HR, marketing, process, and quality. BS in legal sciences, Msc in Performance Management
PhD in Information Technology with 15+ years of research experience in Machine Learning and Stochastic Optimization
PhD in Theoretical and Computational Physics, researcher in Machine Learning with 10+ years of experience
Final year PhD Student in Computer Science with 4+ years in Machine Learning Research and 3+ as Software Engineer
4+ years in Software Development. BS in Automation and Computer Science. External collaborator
15+ years in management, legal, HR, marketing, process, and quality. BS in legal sciences, Msc in Performance Management
At Quaesta AI we provide tailored solutions based on Artificial Intelligence and Machine Learning, and we support you in the integration in your products or services of the most advanced technologies coming from the latest breakthroughs in scientific research.
Our mission is to allow companies and startups to access advanced technologies quickly and without unnecessary efforts. Let us discuss and identify together your needs and based on that we will design effective and efficient solutions which will bring your business to the next level.
Luigi and Riccardo met in Romania in 2017, working in a European-funded research project in the field of Machine Learning and Deep Learning. In 2021, motivated by a strong interest to develop industrial applications of their research, they decided to found Quaesta AI, with the purpose of supporting businesses and startups in accessing novel solutions based on most recent advances in Deep Learning and Computer Vision research.
Luigi obtained a master in Computer Science Engineering in 2007 followed by a PhD in Information Technology in 2011 both from Politecnico di Milano. Before moving to Cluj-Napoca in 2016 as Project Director of the DeepRiemann project, he worked as a postdoc at Università Statale di Milano and as Assistant Professor at Shinshu University, Nagano in Japan.
Riccardo obtained his degree in Mathematical Engineering from Università degli Studi di Firenze, he visited the Institut für Theoretische Physik in Graz, and obtained his PhD from Linköping University in Theoretical and Computational Physics. He progressively became passionate for Machine Learning and decided to move to Cluj-Napoca for a postdoc in the DeepRiemann project.
Quaesta AI represents the next exciting challenge in their professional careers.
created with
Website Builder Software .