Numerical and symbolical fusion applied to recognition from image database

A numerical and symbolical fusion approach is presented in this paper in order to propose a way for knowledge coding and reasoning modelling. This approach is based on data processing formalism aiming to link information extractors and their functional representation including also quantitative estimators and interval of validity to maintain information consistency. This paper presents illustrations about the numerical and symbolical formalism aiming to specify detectors and recognizers from simple to complex functionalities, parking surveillance and structural classes of targets detection, and the formalization of the detection and recognition functions.