The Data Science and AI for iGaming event was organised by , a no-code data science platform that can be used to analyse data with advanced Deep Learning, AutoML, and Causal AI. More information about the event can be found online.
The Deep-FIR project concerns the research and development of AI techniques that are primarily based on deep learning to improve the quality of images and videos acquired from devices such as mobile phone cameras and CCTV cameras, which tend to yield low quality images due to a number of factors such as compression, poor lighting, motion blur, low resolution, and wide angle lenses that can capture a wide field of view at the expense of decreasing the number of pixels representing an object.
This research, being carried out within the field known as ‘super-resolution’, will enable the retrieval of important information from images or videos, such as clearer faces or vehicle license plates to help apprehend perpetrators. Hence, it will be particularly useful to law enforcement agencies, forensics laboratories, and security companies. However, there also exist other applications, such as restoration of old photos and multispectral satellite imagery, among others.
One of the novelties currently being investigated concerns how the real-world degradations afflicting an image can be estimated, and how this information can be used to help guide the super-resolution algorithm in yielding clearer and more satisfactory images.
More information about Deep-FIR can be found on the project website, the project’s , and the newly-created . The project was also recently featured in the
The Deep-FIR project is being done in collaboration with Ascent Software and is financed by the Malta Council for Science & Technology (MCST), for and on behalf of the Foundation for Science & Technology, through the FUSION: R&I Technology Development Programme.
