Remote bar-code localisation using mathematical morphology

Bar-code labels are used in industry to identify and classify a wide variety of products, tools and equipment, their reading generally being undertaken via a laser scanning system. In most cases the number, position and orientation of the bar-codes are well known. However, a particular application under consideration here involves the identification of radioactive material containers via their bar-codes, in which general safety requirements demand remote identification (at least five metre distant) and where laser scanning cannot be used. The images acquired can contain more than one bar-code and these can be found in varying positions within the field of view. Furthermore the container bar code labels are known to occur in random position and orientation. This work focuses on a computer vision based solution to this problem in which the bar-codes are remotely located from within a general grey scale image using a morphological based processing and algorithm. The final solution utilises a pipelined architecture to obtain near real-time operation