3D Face Recognition for Cows

This master’s thesis assignment presents a method to recognize cows using their 3D face point clouds. Face is chosen because of the rigid structure of the skull compared to other parts. The 3D face point clouds are acquired using a newly designed dual RGBD camera setup. After registering the 3D faces to a specific pose, the cow ID is determined by running Iterative Closest Point (ICP) method on the probe against all the point clouds in the gallery. The identification results are based on the the mean squared distance of between the ICP correspondences called inlier root mean square error (RMSE). In a closed set of 32 cows with 5 point clouds per cow in the gallery, the ICP recognition demonstrates an almost perfect identification rate of 99.37% to 100%.