AN APPROACH TO IMAGE OBJECTS RECOGNITION AND INTERPRETATION
Tudor Barbu · 2003
We have focused on a set of problems related to image pattern recognition, presenting an approach for the graphical objects' detection problem. First, in the introduction, we describe the general aspects of the computer vision system. Then, we provide approaches for image's objects identification, by composing the previously detected textured and non--textured regions, for the shape classification of the obtained objects and for a structure-based clustering of those image objects. Finally, after completing the steps of extraction and recognition, an objects' interpretation method is proposed. Our methods' results could be further applied in image retrieval and image understanding domains.