|
Web
Education
Viewing 1-4 of 4 total results
3D reconstruction and face recognition using kernel-based ...
Research highlights We propose an improved kernel-independent component analysis method to reconstruct 3D human faces. A three-layer feed-forward neural network trained by a back-propagation algorithm is used to realize a classifier. The experimental results demonstrate that the proposed method is efficient in reconstruction and face recognition applications....
 3D Reconstruction and Face Recognition Using Kernel-Based ...
Keywords: Independent component analysis, 3D human face reconstruction, 3D human face recognition, back-propagation algorithm, neural networks. 1. Introduction When we use a camera to capture 3D objects, we lose the depth information of the 3D objects and only obtain the 2D image information. However, the depth information of the 3D objects ......
Appearance-based three-dimensional object recognition ...
Recognition was then performed by locating the closest point in the manifold using radial basis function network, which gave the identity and view (or pose) of the object. The use of ICA, in place of principle component analysis is expected to give a `natural' manifold with maximum significant information with least redundancy.
Three-dimensional computational holographic imaging and ...
We present computational holographic three-dimensional imaging and automated object recognition based on independent component analysis (ICA). Three-dimensional sensing of the scene is performed by computational holographic imaging of the objects using phase-shifting digital holography.
|
