Relative Image Measurement on Cigarette Filter Tip

Cigarette filter tip is a deformable and irregular shape wok piece; it could not be measured by traditional instruments. This paper put forward a novel computer vision measurement: relative measurement based on image analysis. In this method a standard work piece and a measured work piece were put in the same imaging fields, measured image was collected by CCD camera. Wavelet has been used to remove noise, Sobel detector to detect image edge, and an improved randomized Hough algorithm to detect circles. It improves the precision of image location and the efficient of image processing. The standard part´s roundness error was evaluated by minimum region Law. The cigarette filter tip´s circumference and roundness errors have been calculated by comparing with the standard´s dimensions (relative method). An algorithm for edge sub pixel location based on Zernike moment mask of square was used to calculate measured valuables. The results show that the relative method accuracy based on the single pixel edge image was good enough to the results based on the sub-pixel edge image. Experiments show this method is applicable, simple, precise and robust.