CIEDE 2000 in 5% of the standard processing time with the same accuracy level powered by the use of a patented computer-implemented method based on a new set of digital filters.
The usage of colour similarity algorithms has been increasingly important in several fields such as Multimedia, Healthcare, Agro-food, or Materials, which require image and video analysis and processing, content management, and real colour comparison. Colour identification presents challenges mostly related to the image’s noise and illumination and the computational cost, complexity, or time to comply with recommended standard metrics (CIEDE2000). These limitations hinder real-time or portable applications.
INESC TEC developed an improved computer-implemented method to calculate CIEDE2000 reducing up to 95% the computational powerusually required by the conventional implementation of this international standard of human colour perception.
At the heart of this technology is an innovative set of filtering modules where simpler calculations are performed and an assessment is made, leading todecreased computation time. This improvement allows determining CIEDE2000 in real-time video as well as in portable applications.
Examples of such application topics are mineral identification, dental ceramics, wine color analysis, corrosion detection and, in a more generic field, image segmentation.
Current development status