Processing and recognition of characters in container codes

This paper describes the process of location and recognition of container code characters. The system has to deal with outdoor images. Top hat transformation, segmentation algorithms and filters have been applied in order to locate the container’s registration number. Our aim is to obtain a list of characters which contains all, or as much as possible, characters of the container’s registration number in order to recognize them. This work is part of a higher order project whose aim is the automation of the entrance gate of a port. Key–Words: computer vision, segmentation, character recognition.