Proceedings - International Conference on Image Processing · 2003 · 42 citations · 4 references
ComputingComputer ScienceComputational GeometryComputer VisionMachine Vision3D ReconstructionDepth EstimationFace RecognitionFacial ReconstructionSurface ReconstructionThree-dimensional Reconstruction3D Facial Reconstruction3D Shape Reconstruction3D Surface ReconstructionHidden Markov Model TrainingHuman Body ReconstructionLearning-based Surface Reconstruction
In this paper, a novel method of the surface reconstruction from a single monocular image is proposed. Our proposed approach (called shape from knowledge) is based on the knowledge of objects, which is acquired by learning from a number of samples. To achieve this, we investigate making use of the hidden Markov model (HMM) framework, which models the correspondence between an intensity image an its depth information. We have applied our algorithm to the 3-D face and 3-D hand reconstruction from single images, and the results show the effectiveness of the proposed method.
4
XM2VTSDB: The Extended M2VTS Database
Kieron Messer, Jiřı́ Matas, Josef Kittler et al. · 1999 · 1.2K citations · Full text
An embedded HMM-based approach for face detection and recognition
Ara Nefian, M.H. Hayes · 1999 · 162 citations