CoSi - Method and Device for Colour Similarity Evaluation

Colour differences are of great importance in many applications, particularly when image processing or computer vision techniques are to be employed.
The CoSi technology can evaluate colour similarity, i.e., comparing two colours in a low processing time. It is applicable to areas such as Multimedia, Healthcare and Agro-food.

- Challenge | Opportunity
The usage of colour similarity algorithms has been increasingly important in several fields of application, such as: image and video analysis and processing, content management, or real colour comparison. All these use image segmentation, often a critical step, whose outcome affects the results of the following processing possibly preventing proper operation.
Despite the many years of research, image segmentation is still an unresolved research topic, with colour identification playing a key role. Its main challenges are: the noise resulting from the segmentation; the computational cost, complexity, or time to comply with recommended metrics (which prevents its application in many scenarios, particularly those with real time constraints or portability needs); and finally they can be severely affected by illumination and the discrimination between closer colours is rarely easy.
Nevertheless, many industries benefit from these algorithms and they all have in common several requirements, namely: quickness, low processing complexity, and high accuracy, which are addressed by this technology.