Papers by Keyword: 3D Data

Abstract: Reverse engineering and spatial digitization became more popular recently. The popularity grows with the devices which are capable to scan the human figures, cars, parts of the buildings or even bigger objects in a single process. In general, scanning devices sometimes present disproportionate costs as the usual additional software often tops the half of the hardware price. Text of this paper is focused on the alternative device which can use very affordable software applications to generate the same results as the most expensive scanning equipment. Particular parts of this article briefly describe the principles of non-contact three dimensional scanning using the Kinect device, the process of data processing in alternative software applications and possibilities of their further utilization.

Abstract: In this paper, an approach based on local curvature feature matching for 3D face recognition is proposed. K-L transformation is employed to adjust coordinate system and coarsely align 3D point cloud. Based on B-splines approximation, 3D facial surface reconstruction is implemented. Through analyzing curvature features of the fitted surface, local rigid facial patches are extracted. According to the extracted local patches, feature vectors are constructed to execute final recognition. Experimental results demonstrate high performance of the presented method and also show that the method is fairly effective for 3D face recognition.