Our technology is transforming sub-sampling imaging across a wide number of sectors across the globe.
Our Technology
Key Features
Patented technology
SenseAI is based on decades of academic research globally and more recently at University of Liverpool in the UK. The core technology is embodied in a series of patents as well as software knowhow developed over a long period.
Inpainting Algorithm
Sub-sampling techniques initially take random samples of the image which is then complemented by an ultra-fast implementation of an inpainting algorithm, developed from the ground up to be a world leader in high quality image inpainting applications, as well as flexible enough to be robust across a wide range of applications.
Easy implementation
No lengthy or costly training data is required, and the methods can be implemented with a push of a button.
Our Technology
SenseAI is a suite of AI technologies which dramatically changes how image sensing is used. Using proprietary sub-sampling methodologies, it can generate the same high-quality images and video feeds with up to 100x less data (1% of the original data). This can massively speed up imaging of all kinds in many industries – electron microscopy, medical imaging, satellites, CCTV and more.
By having such quick processing, it can unlock automation and other capabilities too. For applications where dosage is an issue (X-ray, electron microscopy) the reduced beam density also has significant benefits.
Transforming how institutions process, store and use image sensing
Frequently asked questions
At its core, SenseAI utilises an ultra-fast implementation of the beta process factor analysis (BPFA) algorithm. BPFA is used to learn a sparse representation of a dataset, which is then used to reconstruct that entire dataset. Unlike many other algorithms, BPFA is a blind inpainting algorithm, meaning that it can learn a dictionary from both fully sampled and subsampled data.
Subsampling is a core component of the SenseAI workflow, and involves the deliberate formation of incomplete datasets. By sampling a fraction of the data, such as only a handful of pixels within an image, subsampled data can be produced and processed using SenseAI. Subsampling can be achieved by manipulating scanning hardware, implementing novel detector designs, or operating in low signal conditions, and in almost all cases can aid in increasing the speed of data acquisition.
Subsampling can be applied to nearly every imaging platform, though the form it takes will depend on the system. In all cases, an incomplete dataset is formed – this means faster acquisition times and faster processing times. In scanning systems, the imaging flux can also be reduced, meaning that not only can information be acquired faster, but with less damage to sensitive materials.