Appearance changes due to viewing angle changes cause difficulties for most of the gait recognition methods. In this paper, we propose a new approach for multi-view recognition, which allows to recognize people walking on curved paths. The recognition is based on 3D angular analysis of the movement of the walking human. A coarse-to-fine gait signature represents local variations on the angular measurements along time. A Support Vector Machine is used for classifying, and a sliding temporal window for majority vote policy is used to smooth and reinforce the classification results. The proposed approach has been experimentally validated on the publicly available ``Kyushu University 4D Gait Database''. The results show that this new approach achieves promising results in the problem of gait recognition on curved paths.