HMM-based surface reconstruction from single images
Authors:
- T. NaruseTNT. Naruse
- M. IkeharaMIM. Ikehara
- A. KurematsuAKA. Kurematsu
- 25 June 2003
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2 (15224880)
Abstract
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.Keywords
This publication has 4 references indexed in Scilit:
- Recovery of 3-D face structure using recognition2002
- Discovery and segmentation of activities in videoIEEE Transactions on Pattern Analysis and Machine Intelligence, 2000
- An embedded HMM-based approach for face detection and recognition1999
- Keyword spotting in poorly printed documents using pseudo 2-D hidden Markov modelsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1994