Vision inspection system for holograms with mixed patterns

We propose an vision inspection system for hologram with mixed patterns. The system hardware consists of LED illuminator, CCD camera, and vision processor. The LEDs of illuminator emit alternatively and change the incident angle to acquire each image of pattern. The system software consists of the stages of pattern generation and pattern matching. The acquired images of hologram are compared with their reference images by matching algorithm. Since the several patterns are mixed in one hologram, the reference image should be changed if the hologram is rotated. To compensate for the positioning error of hologram, reference images are generated in on-line. We apply a frequency-transformation based CGH (computer-generated hologram) method to generate reference images. For the fast pattern matching, we also apply the matching method in the frequency domain. Experimental results using holograms attached at Korean currency are then presented to verify the usefulness of the proposed system.