An algorithm for speaker's lip contour extraction is presented in this paper. A color video sequence of speaker's face is acquired, under natural lighting conditions and without any particular make-up. First, a logarithmic color transform is performed from RGB to HI (hue, intensity) color space. A bayesian approach segments the mouth area using Markov random field modelling. Motion is combined with red hue lip information into a spatiotemporal neighbourhood. Simultaneously, a Region Of Interest and relevant boundaries points are automatically extracted. Next, an active contour using spatially varying coefficients is initialised with the results of the preprocessing stage. Finally, an accurate lip shape with inner and outer borders is obtained with good quality results in this challenging situation.
HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L'archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d'enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.
Using stereo photogrammetry to obtain digital elevation models (DEMs) for surface topography analysis is becoming popular in hydraulic research, especially for coarse gravel beds. This paper assesses the DEM quality by using a realistic 3D printed gravel-bed model, with known elevations every 0Á25 mm, as ground truth. Two Nikon D5100 cameras and non-proprietary photogrammetric software for camera calibration and DEM reconstruction are used for the study. A measured DEM is compared point by point with the ground truth and displays a very high measurement accuracy. The 3D printing of ground truths facilitates fast and versatile evaluation of both the DEM quality and the sensitivity of its errors to changes in surface topography and collection parameters. It has the potential to streamline evaluations of calibration and image quality, as well as error filtering strategies. Ultimately, 3D printed models will help in exploring stereomatching error reductions in occluded regions and defining the most suitable strategy for gravel-bed DEM collection, both in air and through water.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.