The paper deals with the design and new solutions of application software with the aim to detect and recognize objects sensed by a camera. Objects of the sensed scene were determined and recognized after previous digital processing of data delivered by the camera. To this end the computer vision learning neural-based methods of feature extraction were used. The proposed application software may be used in various applications where the tracking of objects and understanding of a real scene is required. The results obtained will be used for teaching and research at the FEI STU in Bratislava.

No abstract