Feature Recognition of Concave-Convex Shape Based on Single Image

A method of shape feature recognition based on single image is proposed to solve the problem of shape structure deformation and the concave-convex ambiguity in the current recognition method. Firstly, the surface orientation and height values of the object are extracted by Shape from Shading. Then, the surface shape index is applied to effectively identify the local shape features, which provides important basic information for 3D models. Experiment shows that the feature of the object can be successfully recognized by using this method from the single image, and the method has high efficiency, low complexity and good recognition results.