Hello everyone! This is our first thread in the community, and we’re excited to share what we’re building with the challenge kit!
Project title
A.B.C. ( A.I. Book Cataloguer )
What you’ll be building
We’re developing a next-generation tabletop station that automatically scans a book’s cover, uses an on-device AI model to extract the title, author, and publisher, and instantly displays the results on screen. The operator simply places the book on the surface beneath a camera connected to the Orange Pi running Metis and reviews the output-fast, intuitive, and hands-free.
The system combines an object-recognition model, used to distinguish the operator’s hands from the book itself, with an OCR model that extracts the text of interest directly from the cover, enabling accurate, real-time identification of title, author, and publisher.
If the information is correct, the book is cleared; if not, the operator simply crosses their index fingers to form an X under the camera. This gesture is detected by the same object-recognition model, triggering a bold red "REJECTED" message on the display and signaling that the system should re-scan the book or flag it for review.
Why this project matters to you
We care deeply about this project because it’s an idea we developed last year-one that led us to found Denovo as an innovative startup in the field of AI-driven mechatronics, and a project we’ve been eager to pursue ever since. Thanks to Axelera’s challenge and the Metis kit, we can’t wait to finally bring it to life!
What problem it aims to solve
Our project is designed to solve a well-known challenge in the world of collection digitisation: manual cataloguing is slow, cumbersome, and error-prone. Today, operators must read each book’s data, enter it by hand, and correct any mistakes-a process that significantly slows down workflows and undermines metadata quality.
Our solution eliminates all of this. It automates information extraction and introduces a simple, natural correction gesture, allowing the entire process to become faster, far more accurate, and remarkably intuitive. In short, we tackle the core challenge of digitisation: transforming a repetitive, high-risk task into a smart, efficient, and reliable experience.
Where you think you’ll get started
We actually started thinking about this project last year, at least conceptually. But now we’re ready to move faster, and we can’t wait to receive the kit so we can finally start putting the pieces of the puzzle together, beginning with the hardware setup and the logistical structure needed to run our tests and turn the concept into a working prototype.
Anything else you'd like to add!
We’re a small international team - two Italian engineers and a Polish project manager - and we’re really excited to take part in a European competition in the field of artificial intelligence. We’ve already developed several products on commercial hardware, but this is truly our first real edge-AI project coming to life, and that makes it even more inspiring for us.
