The problem of finding optimal image transformation according to informational image properties is considered. During the research, image informational properties that distinguish images from all other recognition objects were investigated. The notion of image equivalence was introduced. Notion of image equivalence as identity of images with respect to some transformation set was explored. The proposed equivalence definition allows decomposition of image set into subsets of a certain type and establishes correspondence between image equivalence classes and some subsets of operations. On this basis, the method for selecting efficient image recognition algorithm according to image informational nature was elaborated. The proposed method provides a possibility of improving efficiency of selecting image analysis algorithms and automation (partial or complete) of image processing. It allows taking into consideration internal information that image conveys, syntactic and semantic.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.