INVESTIGACIÓN
Publicaciones
Todas las publicaciones:
Lo sentimos, no hay publicaciones que cumplan este criterio.
Buscar Publicación:
Castro-Martinez, Francisco Javier; Castelan, Mario; Lopez-Juarez, Ismael Light Source Intensity Adjustment for Enhanced Feature Extraction Conferencia Advances in Pattern Recognition: Second Mexican Conference on Pattern Recognition, MCPR 2010, Puebla, Mexico, September 27-29, 2010. Proceedings, Springer Berlin Heidelberg, Berlin, Heidelberg, 2010, ISBN: 978-3-642-15992-3. Castelan, Mario; Arechavaleta, Gustavo Approximating the reachable space of human walking paths: a low dimensional linear approach Conferencia 2009 9th IEEE-RAS International Conference on Humanoid Robots, 2009, ISSN: 2164-0572. Hernandez-Rodriguez, Felipe; Castelan, Mario A Mobile Data Acquisition Platform for Photometric Stereo Conferencia 2009 Electronics, Robotics and Automotive Mechanics Conference (CERMA), 2009. Castelan, Mario; Van Horebeek, Johan Relating intensities with three-dimensional facial shape using partial least squares Artículo de revista En: IET Computer Vision, vol. 3, no 2, pp. 60-73, 2009, ISSN: 1751-9632. Castelan, Mario; Puerto-Souza, Gustavo; Van Horebeek, Johan Using Subspace Multiple Linear Regression for 3D Face Shape Prediction from a Single Image Conferencia Advances in Visual Computing: 5th International Symposium, ISVC 2009, Las Vegas, NV, USA, November 30-December 2, 2009. Proceedings, Part II, Springer Berlin Heidelberg, Berlin, Heidelberg, 2009, ISBN: 978-3-642-10520-3. Castelan, Mario; Van Horebeek, Johan 3D face shape approximation from intensities using Partial Least Squares Conferencia 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, 2008, ISSN: 2160-7508. Castelan, Mario; Smith, William A P; Hancock, Edwin R A Coupled Statistical Model for Face Shape Recovery From Brightness Images Artículo de revista En: IEEE Transactions on Image Processing, vol. 16, no 4, pp. 1139-1151, 2007, ISSN: 1057-7149. Castelan, Mario; Hancock, Edwin R Face Shape Recovery and Recognition Using a Surface Gradient Based Statistical Model Conferencia Computer Analysis of Images and Patterns: 12th International Conference, CAIP 2007, Vienna, Austria, August 27-29, 2007. Proceedings, Springer Berlin Heidelberg, Berlin, Heidelberg, 2007, ISBN: 978-3-540-74272-2. Torres-Mendez, Luz Abril; Ramirez-Sosa Moran, Marco I; Castelan, Mario A Single-Frame Super-Resolution Innovative Approach Conferencia MICAI 2007: Advances in Artificial Intelligence: 6th Mexican International Conference on Artificial Intelligence, Aguascalientes, Mexico, November 4-10, 2007. Proceedings, Springer Berlin Heidelberg, Berlin, Heidelberg, 2007, ISBN: 978-3-540-76631-5. Castelan, Mario; Almazan-Delfin, Ana Judith; Ramirez-Sosa Moran, Marco I; Torres-Mendez, Luz Abril Example-Based Face Shape Recovery Using the Zenith Angle of the Surface Normal Conferencia MICAI 2007: Advances in Artificial Intelligence: 6th Mexican International Conference on Artificial Intelligence, Aguascalientes, Mexico, November 4-10, 2007. Proceedings, Springer Berlin Heidelberg, Berlin, Heidelberg, 2007, ISBN: 978-3-540-76631-5. Castelan, Mario; Hancock, Edwin R Acquiring height data from a single image of a face using local shape indicators Artículo de revista En: Computer Vision and Image Understanding, vol. 103, no 1, pp. 64 - 79, 2006, ISSN: 1077-3142. Castelan, Mario; Hancock, Edwin R Using Cartesian Models of Faces with a Data-Driven and Integrable Fitting Framework Conferencia Image Analysis and Recognition: Third International Conference, ICIAR 2006, P'ovoa de Varzim, Portugal, September 18-20, 2006, Proceedings, Part II, Springer Berlin Heidelberg, Berlin, Heidelberg, 2006, ISBN: 978-3-540-44896-9. Castelan, Mario; Hancock, Edwin R A Simple Coupled Statistical Model for 3D Face Shape Recovery Conferencia 18th International Conference on Pattern Recognition (ICPR'06), vol. 1, 2006, ISSN: 1051-4651. Castelan, Mario; Hancock, Edwin R A Facial Statistical Model from Complex Numbers Conferencia 18th International Conference on Pattern Recognition (ICPR'06), vol. 1, 2006, ISSN: 1051-4651. Castelan, Mario; Hancock, Edwin R A comparison of Cartesian coordinate-based representations for building three-dimensional models of faces Conferencia IEEE International Conference on Image Processing 2005, vol. 2, 2005, ISSN: 1522-4880. Castelan, Mario; Hancock, Edwin R Improved Face Shape Recovery and Re-illumination Using Convexity Constraints Conferencia Image Analysis and Processing -- ICIAP 2005: 13th International Conference, Cagliari, Italy, September 6-8, 2005. Proceedings, Springer Berlin Heidelberg, Berlin, Heidelberg, 2005, ISBN: 978-3-540-31866-8. Castelan, Mario; Hancock, Edwin R Fitting 3D Cartesian Models to Faces Using Irradiance and Integrability Constraints Conferencia Image Analysis and Processing -- ICIAP 2005: 13th International Conference, Cagliari, Italy, September 6-8, 2005. Proceedings, Springer Berlin Heidelberg, Berlin, Heidelberg, 2005, ISBN: 978-3-540-31866-8. Castelan, Mario; Hancock, Edwin R Acquiring height maps of faces from a single image Conferencia Proceedings. 2nd International Symposium on 3D Data Processing, Visualization and Transmission, 2004. 3DPVT 2004., 2004. Castelan, Mario; Hancock, Edwin R Combining data-closeness and Fourier domain integrability constraints in shape-from-shading Conferencia Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004., vol. 3, 2004, ISSN: 1051-4651. Castelan, Mario; Hancock, Edwin R A Method for Re-illuminating Faces from a Single Image Conferencia Progress in Pattern Recognition, Image Analysis and Applications: 9th Iberoamerican Congress on Pattern Recognition, CIARP 2004, Puebla, Mexico, October 26-29, 2004. Proceedings, Springer Berlin Heidelberg, Berlin, Heidelberg, 2004, ISBN: 978-3-540-30463-0.@conference{Castro-Mart\^{i}nez2010,
title = {Light Source Intensity Adjustment for Enhanced Feature Extraction},
author = {Castro-Martinez, Francisco Javier and Castelan, Mario and Lopez-Juarez, Ismael},
editor = {Martinez-Trinidad, Jose Francisco
and Carrasco-Ochoa, Jesus Ariel
and Kittler, Josef},
url = {http://dx.doi.org/10.1007/978-3-642-15992-3_6
http://link.springer.com/chapter/10.1007%2F978-3-642-15992-3_6},
doi = {10.1007/978-3-642-15992-3_6},
isbn = {978-3-642-15992-3},
year = {2010},
date = {2010-01-01},
booktitle = {Advances in Pattern Recognition: Second Mexican Conference on Pattern Recognition, MCPR 2010, Puebla, Mexico, September 27-29, 2010. Proceedings},
pages = {50--60},
publisher = {Springer Berlin Heidelberg},
address = {Berlin, Heidelberg},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
@conference{5379595,
title = {Approximating the reachable space of human walking paths: a low dimensional linear approach},
author = {Castelan, Mario and Arechavaleta, Gustavo },
url = {http://ieeexplore.ieee.org/document/5379595/?arnumber=5379595},
doi = {10.1109/ICHR.2009.5379595},
issn = {2164-0572},
year = {2009},
date = {2009-12-01},
booktitle = {2009 9th IEEE-RAS International Conference on Humanoid Robots},
pages = {81-86},
abstract = {In this work, we aim to exhibit the geometrical shape primitives of human walking trajectories using a statistical model constructed through Principal Component Analysis. This analysis provides sufficient information to derive a linear human-like path generator based on examples. The examples are provided by a motion capture database of human walking trajectories. The proposed model captures the shape of trajectories in terms of path length and deformation. We have successfully applied our model to compute a good approximation of the reachable space of human walking. This can be done with a negligible computational cost since it is based on a linear combination of basis human paths.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
@conference{5341996,
title = {A Mobile Data Acquisition Platform for Photometric Stereo},
author = {Hernandez-Rodriguez, Felipe and Castelan, Mario},
url = {http://ieeexplore.ieee.org/document/4563049/?arnumber=4563049},
doi = {10.1109/CERMA.2009.76},
year = {2009},
date = {2009-09-01},
booktitle = {2009 Electronics, Robotics and Automotive Mechanics Conference (CERMA)},
pages = {163-168},
abstract = {The photometric stereo method (PSM) is a well known technique in the computer vision field that recovers 3D shape from a set of images of a still scene, using a single fixed-pose camera. Every image in the set is taken while a change in the direction of the light source occurs. Commonly, the acquisition of PMS imagery implies using rigid platforms with a static configuration of light sources. In this paper, we explore the use of a mobile platform as an alternative way to obtain PSM imagery. Using a 5 DOF robotic arm, a light source (placed over the end effector of the robot) is moved around an object so as to observe constraints concerning the elevation and azimuth angle of the illumination vector. These constraints are based on work by Drbohlav and Chantler, where a theoretical study about an optimal lightning configuration is introduced. Experiments with objects showing varying reflectance properties demonstrate the feasibility of the mobile platform for the purposes of gathering PSM imagery.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
@article{5069092,
title = {Relating intensities with three-dimensional facial shape using partial least squares},
author = {Castelan, Mario and Van Horebeek, Johan},
url = {http://ieeexplore.ieee.org/document/4563049/?arnumber=4563049},
doi = {10.1049/iet-cvi.2008.0060},
issn = {1751-9632},
year = {2009},
date = {2009-06-01},
journal = {IET Computer Vision},
volume = {3},
number = {2},
pages = {60-73},
abstract = {The authors apply partial least squares regression to predict three-dimensional (3D) face shape from a single image. PLS describes the relationship between independent (intensity images) and dependent (3D shape) variables by seeking directions in the space of independent variables that are associated with large variations in the space of dependent variables. We use this idea to construct statistical models of intensity and 3D shape that capture strongly linked variations in both spaces. This decomposition leads to the construction of two different models that capture common variations in 3D shape and intensity. Using the intensity model, a set of parameters is obtained from out-of-training intensity examples. These intensity parameters can then be used directly in the 3D shape model to approximate facial shape. Experiments show that prediction is achieved with reasonable accuracy, improving results obtained through canonical correlation analysis.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
@conference{Castel\'{a}n2009,
title = {Using Subspace Multiple Linear Regression for 3D Face Shape Prediction from a Single Image},
author = {Castelan, Mario and Puerto-Souza, Gustavo and Van Horebeek, Johan },
url = {http://dx.doi.org/10.1007/978-3-642-10520-3_63},
doi = {10.1007/978-3-642-10520-3_63},
isbn = {978-3-642-10520-3},
year = {2009},
date = {2009-01-01},
booktitle = {Advances in Visual Computing: 5th International Symposium, ISVC 2009, Las Vegas, NV, USA, November 30-December 2, 2009. Proceedings, Part II},
pages = {662--673},
publisher = {Springer Berlin Heidelberg},
address = {Berlin, Heidelberg},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
@conference{4563049,
title = {3D face shape approximation from intensities using Partial Least Squares},
author = {Castelan, Mario and Van Horebeek, Johan},
url = {http://ieeexplore.ieee.org/document/4563049/?arnumber=4563049},
doi = {10.1109/CVPRW.2008.4563049},
issn = {2160-7508},
year = {2008},
date = {2008-06-01},
booktitle = {2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops},
pages = {1-8},
abstract = {In this paper, we apply partial least squares (PLS) regression to predict 3D face shape from a single image. PLS describes the relationship between independent (intensity images) and dependent (3D shape) variables by seeking directions in the space of the independent variables that are associated with high variations in the dependent variables. We exploit this idea to construct statistical models of intensity and 3D shape that express strongly linked variations in both spaces. The outcome of this decomposition is the construction of two different models which express coupled variations in 3D shape and intensity. Using the intensity model, a set of parameters is obtained from out-of-training intensity examples. These intensity parameters can then be used directly in the 3D shape model to approximate facial shape. Experiments show that prediction is achieved with reasonable accuracy.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
@article{4130415,
title = {A Coupled Statistical Model for Face Shape Recovery From Brightness Images},
author = {Castelan, Mario and Smith, William A P and Hancock, Edwin R },
url = {http://ieeexplore.ieee.org/document/4130415/?arnumber=4130415},
doi = {10.1109/TIP.2006.891351},
issn = {1057-7149},
year = {2007},
date = {2007-04-01},
journal = {IEEE Transactions on Image Processing},
volume = {16},
number = {4},
pages = {1139-1151},
abstract = {We focus on the problem of developing a coupled statistical model that can be used to recover facial shape from brightness images of faces. We study three alternative representations for facial shape. These are the surface height function, the surface gradient, and a Fourier basis representation. We jointly capture variations in intensity and the surface shape representations using a coupled statistical model. The model is constructed by performing principal components analysis on sets of parameters describing the contents of the intensity images and the facial shape representations. By fitting the coupled model to intensity data, facial shape is implicitly recovered from the shape parameters. Experiments show that the coupled model is able to generate accurate shape from out-of-training-sample intensity images},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
@conference{Castel\'{a}n2007,
title = {Face Shape Recovery and Recognition Using a Surface Gradient Based Statistical Model},
author = {Castelan, Mario and Hancock, Edwin R},
editor = {Kropatsch, Walter G.
and Kampel, Martin
and Hanbury, Allan},
url = {http://dx.doi.org/10.1007/978-3-540-74272-2_50},
doi = {10.1007/978-3-540-74272-2_50},
isbn = {978-3-540-74272-2},
year = {2007},
date = {2007-01-01},
booktitle = {Computer Analysis of Images and Patterns: 12th International Conference, CAIP 2007, Vienna, Austria, August 27-29, 2007. Proceedings},
pages = {399--407},
publisher = {Springer Berlin Heidelberg},
address = {Berlin, Heidelberg},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
@conference{Torres-M\'{e}ndez2007,
title = {A Single-Frame Super-Resolution Innovative Approach},
author = {Torres-Mendez, Luz Abril and Ramirez-Sosa Moran, Marco I and Castelan, Mario },
editor = {Gelbukh, Alexander
and Kuri Morales, Angel Fernando},
url = {http://dx.doi.org/10.1007/978-3-540-76631-5_61},
doi = {10.1007/978-3-540-76631-5_61},
isbn = {978-3-540-76631-5},
year = {2007},
date = {2007-01-01},
booktitle = {MICAI 2007: Advances in Artificial Intelligence: 6th Mexican International Conference on Artificial Intelligence, Aguascalientes, Mexico, November 4-10, 2007. Proceedings},
pages = {640--649},
publisher = {Springer Berlin Heidelberg},
address = {Berlin, Heidelberg},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
@conference{Castel\'{a}n2007b,
title = {Example-Based Face Shape Recovery Using the Zenith Angle of the Surface Normal},
author = {Castelan, Mario and Almazan-Delfin, Ana Judith and Ramirez-Sosa Moran, Marco I and Torres-Mendez, Luz Abril },
editor = {Gelbukh, Alexander
and Kuri Morales, Angel Fernando},
url = {http://dx.doi.org/10.1007/978-3-540-76631-5_72},
doi = {10.1007/978-3-540-76631-5_72},
isbn = {978-3-540-76631-5},
year = {2007},
date = {2007-01-01},
booktitle = {MICAI 2007: Advances in Artificial Intelligence: 6th Mexican International Conference on Artificial Intelligence, Aguascalientes, Mexico, November 4-10, 2007. Proceedings},
pages = {758--768},
publisher = {Springer Berlin Heidelberg},
address = {Berlin, Heidelberg},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
@article{Castel\'{a}n200664,
title = {Acquiring height data from a single image of a face using local shape indicators},
author = {Castelan, Mario and Hancock, Edwin R },
url = {http://www.sciencedirect.com/science/article/pii/S1077314206000257},
doi = {http://dx.doi.org/10.1016/j.cviu.2006.03.001},
issn = {1077-3142},
year = {2006},
date = {2006-01-01},
journal = {Computer Vision and Image Understanding},
volume = {103},
number = {1},
pages = {64 - 79},
abstract = {This paper describes work aimed at developing a practical scheme for face analysis using shape-from-shading. Existing methods have a tendency to recover surfaces in which convex features such as the nose are imploded. This is a result of the fact that subtle changes in the elements of the field of surface normals can cause significant changes in the corresponding integrated surface. To overcome this problem, in this paper, we describe a local shape based method for imposing convexity constraints. We show how to modify the orientations in the surface gradient field using critical points on the surface and local shape indicators. The method is applied to both surface height recovery and face re-illumination. Experiments show that altering the field of surface normals so as to impose convexity results in greatly improved height reconstructions and more realistic re-illuminations.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
@conference{Castel\'{a}n2006,
title = {Using Cartesian Models of Faces with a Data-Driven and Integrable Fitting Framework},
author = {Castelan, Mario and Hancock, Edwin R },
url = {http://dx.doi.org/10.1007/11867661_13},
doi = {10.1007/11867661_13},
isbn = {978-3-540-44896-9},
year = {2006},
date = {2006-01-01},
booktitle = {Image Analysis and Recognition: Third International Conference, ICIAR 2006, P'ovoa de Varzim, Portugal, September 18-20, 2006, Proceedings, Part II},
pages = {134--145},
publisher = {Springer Berlin Heidelberg},
address = {Berlin, Heidelberg},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
@conference{1698875,
title = {A Simple Coupled Statistical Model for 3D Face Shape Recovery},
author = {Castelan, Mario and Hancock, Edwin R},
url = {http://ieeexplore.ieee.org/document/1698875/?arnumber=1698875},
doi = {10.1109/ICPR.2006.175},
issn = {1051-4651},
year = {2006},
date = {2006-01-01},
booktitle = {18th International Conference on Pattern Recognition (ICPR'06)},
volume = {1},
pages = {231-234},
abstract = {We focus on the problem of developing coupled statistical models that can be used to recover surface height from brightness images of faces. Our approach consists on using a simple model that assumes that the height eigenmodes are identical to the intensity eigenmodes. We recover the height function directly from the best-fit intensity parameters. As a result the computations involve only a straightforward matrix-vector multiplication. Experiments show that this method generate accurate height surfaces from out-of training intensity images},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
@conference{1698876,
title = {A Facial Statistical Model from Complex Numbers},
author = {Castelan, Mario and Hancock, Edwin R},
url = {http://ieeexplore.ieee.org/document/1698876/?arnumber=1698876},
doi = {10.1109/ICPR.2006.61},
issn = {1051-4651},
year = {2006},
date = {2006-01-01},
booktitle = {18th International Conference on Pattern Recognition (ICPR'06)},
volume = {1},
pages = {235-238},
abstract = {In this paper we explore the use of complex numbers as means of representing angular statistics for surface normal data. Our aim is to use the representation to construct a statistical model that can be used to describe the variations infields of surface normals. We focus on the problem of representing facial shape. The fields of surface normals used to train the model are furnished by range images. We compare the complex representation with one based on angles, and demonstrate the advantages of the new method. Once trained, we illustrate how the model can befitted to brightness images by searching for the set of parameters that both satisfy Lambert's law and minimize the integrability error},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
@conference{1530265,
title = {A comparison of Cartesian coordinate-based representations for building three-dimensional models of faces},
author = {Castelan, Mario and Hancock, Edwin R},
url = {http://ieeexplore.ieee.org/document/1530265/?arnumber=1530265},
doi = {10.1109/ICIP.2005.1530265},
issn = {1522-4880},
year = {2005},
date = {2005-09-01},
booktitle = {IEEE International Conference on Image Processing 2005},
volume = {2},
pages = {II-1154-7},
abstract = {We present an experimental analysis of three different ways of constructing three-dimensional statistical models of faces using Cartesian coordinates, namely, height, surface gradient and one based on Fourier domain basis functions. We test the ability of each of the models for dealing with information provided by shape-from-shading. Experiments show that the surface gradient based representation is more robust to noise than alternative Cartesian representations. Moreover, the method can be operated using a simple non-exhaustive parameter adjustment procedure and ensures that the recovered surface satisfies the image irradiance equation as a hard constraint.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
@conference{Castel\'{a}n2005,
title = {Improved Face Shape Recovery and Re-illumination Using Convexity Constraints},
author = {Castelan, Mario and Hancock, Edwin R },
editor = {Roli, Fabio
and Vitulano, Sergio},
url = {http://dx.doi.org/10.1007/11553595_60},
doi = {10.1007/11553595_60},
isbn = {978-3-540-31866-8},
year = {2005},
date = {2005-01-01},
booktitle = {Image Analysis and Processing -- ICIAP 2005: 13th International Conference, Cagliari, Italy, September 6-8, 2005. Proceedings},
pages = {487--494},
publisher = {Springer Berlin Heidelberg},
address = {Berlin, Heidelberg},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
@conference{Castel\'{a}n2005b,
title = {Fitting 3D Cartesian Models to Faces Using Irradiance and Integrability Constraints},
author = {Castelan, Mario and Hancock, Edwin R },
editor = {Roli, Fabio
and Vitulano, Sergio},
url = {http://dx.doi.org/10.1007/11553595_107},
doi = {10.1007/11553595_107},
isbn = {978-3-540-31866-8},
year = {2005},
date = {2005-01-01},
booktitle = {Image Analysis and Processing -- ICIAP 2005: 13th International Conference, Cagliari, Italy, September 6-8, 2005. Proceedings},
pages = {876--883},
publisher = {Springer Berlin Heidelberg},
address = {Berlin, Heidelberg},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
@conference{1335193,
title = {Acquiring height maps of faces from a single image},
author = {Castelan, Mario and Hancock, Edwin R },
url = {http://ieeexplore.ieee.org/document/1335193/?arnumber=1335193},
doi = {10.1109/TDPVT.2004.1335193},
year = {2004},
date = {2004-09-01},
booktitle = {Proceedings. 2nd International Symposium on 3D Data Processing, Visualization and Transmission, 2004. 3DPVT 2004.},
pages = {183-190},
abstract = {We explore how to improve the quality of the height map recovered from faces using shape-from-shading. One of the problems with reliable face surface reconstruction using shape-from-shading is that local errors in the needle map can cause implosion of facial features, and in particular the nose. To overcome this problem in this paper we develop a method for ensuring surface convexity. This is done by modifying the gradient orientations in accordance with critical points on the surface. We utilize a local shape indicator as a criteria to decide which surface normals are to be modified. Experiments show that altering the directions of a surface normal field of a face leads to a considerable improvement in its integrated height map.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
@conference{1334482,
title = {Combining data-closeness and Fourier domain integrability constraints in shape-from-shading},
author = {Castelan, Mario and Hancock, Edwin R },
url = {http://ieeexplore.ieee.org/document/1334482/?arnumber=1334482},
doi = {10.1109/ICPR.2004.1334482},
issn = {1051-4651},
year = {2004},
date = {2004-08-01},
booktitle = {Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.},
volume = {3},
pages = {115-118 Vol.3},
abstract = {This paper describes a shape-from-shading algorithm that combines constraint on data-closeness from Lambert's law and Fourier domain integrability. The data closeness is ensured by constraining surface normals to fall on an irradiance cone, whose axis points in the light source direction and whose apex angle varies with iteration number. The integrability is ensured by projecting the non-integrable set of surface normals to the nearest integrable one by globally minimizing the distance among them in the Fourier domain. The combination of both data-closeness and integrability constraints is aimed to overcome the problem of high dependency on the image irradiances. Experimental results prove that the new method recovers needle maps that are both smooth and integrable and improves height surface stability.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
@conference{Castel\'{a}n2004,
title = {A Method for Re-illuminating Faces from a Single Image},
author = {Castelan, Mario and Hancock, Edwin R },
url = {http://dx.doi.org/10.1007/978-3-540-30463-0_33},
doi = {10.1007/978-3-540-30463-0_33},
isbn = {978-3-540-30463-0},
year = {2004},
date = {2004-01-01},
booktitle = {Progress in Pattern Recognition, Image Analysis and Applications: 9th Iberoamerican Congress on Pattern Recognition, CIARP 2004, Puebla, Mexico, October 26-29, 2004. Proceedings},
pages = {267--274},
publisher = {Springer Berlin Heidelberg},
address = {Berlin, Heidelberg},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}