In order to improve measurement precision and measurement speed for micro size, a new kind of precision measurement method based on support vector regression for micro size parts was put forward. Taking the clip as the study object in this paper to measure micro distance of the clip slot clearance. First, the digital image of the clip was collected by A102FCCD device, and was input into computer by IEEE1394 digital card. Second, the original gray level image with noise was changed into edge information with single-pixel width after it was processed by reducing noise with median filtering, creating a binary image with threshold method and contour extraction, etc. Third, the detected regions were previously determined according to the proportions of clip length and width. Then pixel points on edges in the detected regions made up the training set of corresponding straight line, and the support vector machine for regression(SVR) was trained by the training set and regression function of every detected straight line was obtained, which is the expression of the sub-pixel, and then the clearance distance of clip slot was measured. Measurement precision acquired by support vector regression method is higher than measurement precision acquired by least square linear regression method through experiment contrast. Measurement precision can reach 1.05μm with support vector regression method. Finally, the measurement error was analyzed. Theory analysis and experimental results show that the method proposed is characterized by high speed and high precision.