Automatic image annotation refinement using fuzzy inference algorithms
Marina Ivašić-Kos, Miran Pobar, Slobodan Ribari� · Advances in intelligent systems research/Advances in Intelligent Systems Research · 2015
Facilitating tasks such as image search is one of the goals of image annotation methods that automatically assign keywords to images.In order to achieve as accurate annotation on object level as possible, and to reduce negative influence of misclassified objects on the inference of scenes, a knowledge based refinement of object classification results is proposed.A fuzzy knowledge representation scheme called KRFPNr is used to represent knowledge about objects and their relations.Fuzzy inheritance and intersection algorithms are used to refine the image annotation on object level by discarding or replacing object labels that do not fit the context.