In the research of pig body size measurement based on machine vision, the demand for posture of pig is high. Image frames of ideal posture need manual selection, which limits the application of body size measurement based on machine vision. To improve the image utilization rate and the efficiency of pig body measurement, pig species of Landrace and Large White were taken as the researches object. Kinect camera was used to obtain video data of pigs. An algorithm was proposed which can detect the posture of pig in the image. In this algorithm, the minimum external rectangles were computed to adjust the level of the pig’s body. Head and tail positions were identified by projection and difference methods. Boundary signature was used to determine whether part of the ears was missing. Image skeleton algorithm and Hough transform algorithm were applied to judge whether the pig body was skewed. On this basis, algorithms for measuring pig body size were designed. The top view and side view of video had 52016 frames, respectively. These frames of 103 sets of video data were tested by the posture detection algorithm and body size measuring algorithm. And 2592 frames of ideal posture frames were screened out. It produced high false negatives (432 frames) and very low false positives (0 frames). The results showed that the absolute deviation of body length was small. The body length deviation of each frame was less than 23%, and the consistency of the measurement results was high. The average accuracy of body width was 95.5%, the average accuracy of body height was 96.3%, and the average accuracy of body length was 97.3%. This research can be used to measure pig body size based on machine vision to improve measurement efficiency.