CHARACTER DETECTION AND RECOGNITION SYSTEM OF BEER BOTTLES

摘要

An optical imaging system and a configuration characteristic algorithm are presented to reducethe difficulties in extracting intact characters image with weak contrast, in recognizing characters on fastmoving beer bottles. The system consists of a hardware subsystem, including a rotating device, CCD, 16mm focus lens, a frame grabber card, a penetrating lighting and a computer, and a software subsystem. Thesoftware subsystem performs pretreatment, character segmentation and character recognition. In the pre-treatment, the original image is filtered with preset threshold to remove isolated spots. Then the horizontalprojection and the vertical projection are used respectively to retrieve the character segmentation. Subse-quently, the configuration characteristic algorithm is applied to recognize the characters. The experimentalresults demonstrate that this system can recognize the characters on beer bottles accurately and effectively;the algorithm is proven fast, stable and robust, making it suitable in the industrial environment.