Research On Tube-type Bottle Image Inspecting System Based On Machine Vision

Characterized with auto inspecting ability, high-speed and accuracy, machine vision technology is one of the most important means in medicine packaging and food processing industries. The research aimed at the design of a tube-type bottle image inspecting system based on machine vision, and simulated actual inspection of glass bottles in the laboratory. The main contributions of this dissertation are the foliowings:Firstly, the structure of the inspecting system was introduced. Aiming at the characteristic of medicine tube-type bottle inspection, the dissertation discusses the project as a whole, the selection of acquisition equipment and designing of illumination apparatus. Initial system design objectives have been achieved.Secondly, the dissertation concerns on the application of digital image processing technology to the detection of defect in empty bottle inspection. After the conclusion of the traditional edge detection methods, several novel algorithms for the inspection of empty bottle bottom, mouth and body are put forward. Experiments have proved their efficiency and feasibility.Thirdly, the dissertation introduced the real-time image processing system. Processing algorithms were realized on SEED-VPM642, and the high efficiency and feasibility of TMS320DM642 processor has been proved. Using DSP was an advanced method of improving efficiency of the inspection system.Finally, the software design is accomplished, focusing on the demand of inspection and the characteristic of DSP. A detailed description of the program is provided.