Improvement of Supervised Shape Retrieval by Learning the Manifold Space

Manifold learning is the technique that aims for finding a constructive way to embed the data from a highdimensional space into a low-dimensional one based on non-linear approaches. In this paper a supervised manifold learning method for shape recognition is proposed. The approach is based on learning the manifold space for training samples, and maps the test samples to the learned space by a Generalized Regression Neural Network (GRNN). The main goal in this paper is to propose a new feature vector to coincide semantic with Euclidean distances. To accomplish this, the desired topological manifold is learnt by a global distance driven non-linear feature extraction method. The experimental results indicated that the geometrical distances between the samples on the manifold space are more related to their semantic distance. To fuse the results of shape recognition based on contour and region based methods, the final result of shape recognition is based on committee decision in three manifold spaces. The experimental results confirmed the effectiveness and the validity of the proposed method.