Segmentation Algorithm of Color Block Target Captured by CCD Camera Based on Region Growing

This paper presents a segmentation algorithm of color block target captured by CCD camera based on region growing. In the new medical testing equipment system, CCD camera is needed to get circle target image of the device's detection card section, and find out the coordinates of the image center, delimit and analyze the color blocks, used to judge whether the detected object is normal. In order to satisfy the real-time measurement and high-precision positioning requirements, it is proposed a method which CCD camera gets central of circle target and color block delimitation. First a radius of constrained least squares circle fitting method is used to locate the center of the circle, can quickly detect the multi circle of the image. The region growing method is used to get similar color vector region, then to format the various color regions. This method is called color image segmentation. The experimental results show that, the Segmentation Algorithm of color block target captured by CCD camera Based on a radius of constrained least squares circle fitting and Region growing is effective and has good robustness of the salt and pepper noise, linear, elliptical and other non circle objects; the method is fast, has high precision measurement and good stability, which can meet the detection equipment card of automatic analysis system's requirements.