虚拟现实、可视化技术、数字化和三维图形建模的发展使互联网和专用数据库中三维模型的数量和检索需扣陕速增长,因此提出了一种圈环射线分解投影轮廓的三维模型检索算法。首先,对三维模型进行位姿对准、投影变换和边界提取;然后,对提取的投影轮廓用圆环射线分解的组合方法参数化,并对该参数化函数进行傅立叶分解,得到图形特征;最后,对特征描述符做相似性匹配,计算特征比较值,得到检索结果。实验表明,该种方法对三维模型的检索效果较好。
Recently, as a result of the development of techniques for VR, visualizing, modeling, and digitizing 3D object, the number of available 3D models on Internet and in special databases has been increased, which also affects the development of 3D model retrieval systems. The 3D model retrieval engine is a system which obtains and analyzes the user's query object and retrieves several similar 3D objects. Efficient feature preprocessing, feature extracting and dissimilarity measures are needed in 3D model retrieval systems. A method for computing shape signature for 3D polygonal models was proposed and analyzed. The key idea is to represent the signature of a model by Fourier descriptor sampled from a shape statistics function. Firstly, position alignment, projection transformation and boundary extraction of a 3D model were carried on. Secondly, the contour extracted from projection was parameterized with a combined method of decomposing using circular rays, and then obtained the shape signature by decomposing the pararneterization function with Fourier. Thirdly, signature descriptors of the query object were matched with all the other models in the database in order to search for similar goals. The comparison with other methods indicates the effectiveness of the method.