A research on foot size measurement algorithm based on image

Foot size measurement has a wide range of applications. It can not only be used in medical foot health, evaluate the health index of the foot, improve the health of the human foot, but also provide a large amount of foot data for the study of kinematics. Due to the limitations of measurement equipment and related algorithms, 3D foot measurement cannot be widely used. We proposed a fast and convenient foot measurement method based on deep learning and image segmentation algorithms. The HED model is used to detect the edges of A4 paper; the traditional image segmentation algorithm GrabCut is used for segmentation of the foot area. The results show that the algorithm proposed in this paper has a faster measurement speed and higher accuracy for foot size measurement.