@conference {12453, title = {Recent advances in age and height estimation from still images and video}, booktitle = {2011 IEEE International Conference on Automatic Face \& Gesture Recognition and Workshops (FG 2011)}, year = {2011}, month = {2011/03/21/25}, pages = {91 - 96}, publisher = {IEEE}, organization = {IEEE}, abstract = {Soft-biometrics such as gender, age, race, etc have been found to be useful characterizations that enable fast pre-filtering and organization of data for biometric applications. In this paper, we focus on two useful soft-biometrics - age and height. We discuss their utility and the factors involved in their estimation from images and videos. In this context, we highlight the role that geometric constraints such as multiview-geometry, and shape-space geometry play. Then, we present methods based on these geometric constraints for age and height-estimation. These methods provide a principled means by fusing image-formation models, multi-view geometric constraints, and robust statistical methods for inference.}, keywords = {age estimation, biometrics (access control), Calibration, Estimation, Geometry, height estimation, HUMANS, image fusion, image-formation model fusion, Legged locomotion, multiview-geometry, Robustness, SHAPE, shape-space geometry, soft-biometrics, statistical analysis, statistical methods, video signal processing}, isbn = {978-1-4244-9140-7}, doi = {10.1109/FG.2011.5771367}, author = {Chellapa, Rama and Turaga,P.} } @article {12439, title = {Statistical Computations on Grassmann and Stiefel Manifolds for Image and Video-Based Recognition}, journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence}, volume = {33}, year = {2011}, month = {2011/11//}, pages = {2273 - 2286}, abstract = {In this paper, we examine image and video-based recognition applications where the underlying models have a special structure-the linear subspace structure. We discuss how commonly used parametric models for videos and image sets can be described using the unified framework of Grassmann and Stiefel manifolds. We first show that the parameters of linear dynamic models are finite-dimensional linear subspaces of appropriate dimensions. Unordered image sets as samples from a finite-dimensional linear subspace naturally fall under this framework. We show that an inference over subspaces can be naturally cast as an inference problem on the Grassmann manifold. To perform recognition using subspace-based models, we need tools from the Riemannian geometry of the Grassmann manifold. This involves a study of the geometric properties of the space, appropriate definitions of Riemannian metrics, and definition of geodesics. Further, we derive statistical modeling of inter and intraclass variations that respect the geometry of the space. We apply techniques such as intrinsic and extrinsic statistics to enable maximum-likelihood classification. We also provide algorithms for unsupervised clustering derived from the geometry of the manifold. Finally, we demonstrate the improved performance of these methods in a wide variety of vision applications such as activity recognition, video-based face recognition, object recognition from image sets, and activity-based video clustering.}, keywords = {activity based video clustering, activity recognition, computational geometry, Computational modeling, Data models, face recognition, feature representation, finite dimensional linear subspaces, geometric properties, Geometry, Grassmann Manifolds, Grassmann., HUMANS, Image and video models, image recognition, linear dynamic models, linear subspace structure, Manifolds, maximum likelihood classification, maximum likelihood estimation, Object recognition, Riemannian geometry, Riemannian metrics, SHAPE, statistical computations, statistical models, Stiefel, Stiefel Manifolds, unsupervised clustering, video based face recognition, video based recognition, video signal processing}, isbn = {0162-8828}, doi = {10.1109/TPAMI.2011.52}, author = {Turaga,P. and Veeraraghavan,A. and Srivastava, A. and Chellapa, Rama} } @conference {12452, title = {Towards view-invariant expression analysis using analytic shape manifolds}, booktitle = {2011 IEEE International Conference on Automatic Face \& Gesture Recognition and Workshops (FG 2011)}, year = {2011}, month = {2011/03/21/25}, pages = {306 - 313}, publisher = {IEEE}, organization = {IEEE}, abstract = {Facial expression analysis is one of the important components for effective human-computer interaction. However, to develop robust and generalizable models for expression analysis one needs to break the dependence of the models on the choice of the coordinate frame of the camera i.e. expression models should generalize across facial poses. To perform this systematically, one needs to understand the space of observed images subject to projective transformations. However, since the projective shape-space is cumbersome to work with, we address this problem by deriving models for expressions on the affine shape-space as an approximation to the projective shape-space by using a Riemannian interpretation of deformations that facial expressions cause on different parts of the face. We use landmark configurations to represent facial deformations and exploit the fact that the affine shape-space can be studied using the Grassmann manifold. This representation enables us to perform various expression analysis and recognition algorithms without the need for the normalization as a preprocessing step. We extend some of the available approaches for expression analysis to the Grassmann manifold and experimentally show promising results, paving the way for a more general theory of view-invariant expression analysis.}, keywords = {Databases, Deformable models, Face, face recognition, facial expression analysis, Geometry, Gold, Human-computer interaction, Manifolds, projective transformation, Riemannian interpretation, SHAPE, view invariant expression analysis}, isbn = {978-1-4244-9140-7}, doi = {10.1109/FG.2011.5771415}, author = {Taheri, S. and Turaga,P. and Chellapa, Rama} } @article {12475, title = {Robust Height Estimation of Moving Objects From Uncalibrated Videos}, journal = {IEEE Transactions on Image Processing}, volume = {19}, year = {2010}, month = {2010/08//}, pages = {2221 - 2232}, abstract = {This paper presents an approach for video metrology. From videos acquired by an uncalibrated stationary camera, we first recover the vanishing line and the vertical point of the scene based upon tracking moving objects that primarily lie on a ground plane. Using geometric properties of moving objects, a probabilistic model is constructed for simultaneously grouping trajectories and estimating vanishing points. Then we apply a single view mensuration algorithm to each of the frames to obtain height measurements. We finally fuse the multiframe measurements using the least median of squares (LMedS) as a robust cost function and the Robbins-Monro stochastic approximation (RMSA) technique. This method enables less human supervision, more flexibility and improved robustness. From the uncertainty analysis, we conclude that the method with auto-calibration is robust in practice. Results are shown based upon realistic tracking data from a variety of scenes.}, keywords = {algorithms, Biometry, Calibration, EM algorithm, geometric properties, Geometry, Image Enhancement, Image Interpretation, Computer-Assisted, Imaging, Three-Dimensional, least median of squares, least squares approximations, MOTION, motion information, multiframe measurements, Pattern Recognition, Automated, Reproducibility of results, Robbins-Monro stochastic approximation, robust height estimation, Sensitivity and Specificity, Signal Processing, Computer-Assisted, stochastic approximation, Subtraction Technique, tracking data, uncalibrated stationary camera, uncalibrated videos, uncertainty analysis, vanishing point, video metrology, Video Recording, video signal processing}, isbn = {1057-7149}, doi = {10.1109/TIP.2010.2046368}, author = {Jie Shao and Zhou,S. K and Chellapa, Rama} } @conference {12490, title = {The role of geometry in age estimation}, booktitle = {2010 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)}, year = {2010}, month = {2010/03/14/19}, pages = {946 - 949}, publisher = {IEEE}, organization = {IEEE}, abstract = {Understanding and modeling of aging in human faces is an important problem in many real-world applications such as biometrics, authentication, and synthesis. In this paper, we consider the role of geometric attributes of faces, as described by a set of landmark points on the face, in age perception. Towards this end, we show that the space of landmarks can be interpreted as a Grassmann manifold. Then the problem of age estimation is posed as a problem of function estimation on the manifold. The warping of an average face to a given face is quantified as a velocity vector that transforms the average to a given face along a smooth geodesic in unit-time. This deformation is then shown to contain important information about the age of the face. We show in experiments that exploiting geometric cues in a principled manner provides comparable performance to several systems that utilize both geometric and textural cues. We show results on age estimation using the standard FG-Net dataset and a passport dataset which illustrate the effectiveness of the approach.}, keywords = {age estimation, Aging, Biometrics, computational geometry, Face, Face Geometry, Facial animation, Feature extraction, function estimation problem, geometric face attributes, Geometry, Grassmann manifold, human face modeling, human face understanding, HUMANS, Mouth, regression, Regression analysis, SHAPE, Solid modeling, solid modelling, velocity vector}, isbn = {978-1-4244-4295-9}, doi = {10.1109/ICASSP.2010.5495292}, author = {Turaga,P. and Biswas,S. and Chellapa, Rama} } @article {17967, title = {Persuading Visual Attention through Geometry}, journal = {Visualization and Computer Graphics, IEEE Transactions on}, volume = {14}, year = {2008}, month = {2008/08//july}, pages = {772 - 782}, abstract = {Artists, illustrators, photographers, and cinematographers have long used the principles of contrast and composition to guide visual attention. In this paper, we introduce geometry modification as a tool to persuasively direct visual attention. We build upon recent advances in mesh saliency to develop techniques to alter geometry to elicit greater visual attention. Eye-tracking-based user studies show that our approach successfully guides user attention in a statistically significant manner. Our approach operates directly on geometry and, therefore, produces view-independent results that can be used with existing view-dependent techniques of visual persuasion.}, keywords = {attention;visual, generation;Attention;Awareness;Computer, Geometry, Graphics;Cues;Humans;Photic, Interface;Visual, modification;mesh, perception;, persuasion;art;mesh, saliency;visual, Stimulation;User-Computer}, isbn = {1077-2626}, doi = {10.1109/TVCG.2007.70624}, author = {Kim,Youngmin and Varshney, Amitabh} } @book {13327, title = {Shape Analysis and Structuring}, year = {2008}, month = {2008///}, publisher = {Springer}, organization = {Springer}, abstract = {With a lot of recent developments in the field, this much-needed book has come at just the right time. It covers a variety of topics related to preserving and enhancing shape information at a geometric level. The contributors also cover subjects that are relevant to effectively capturing the structure of a shape by identifying relevant shape components and their mutual relationships.}, keywords = {Computer Graphics, Computer vision, Computers / Computer Graphics, Computers / Image Processing, Geometrical models, Geometry, Geometry, Analytic, Image analysis, IMAGE PROCESSING, Mathematics / Functional Analysis, Mathematics / Geometry / General, Mathematics / Graphic Methods, Mathematics / Mathematical Analysis, shapes, Technology \& Engineering / Engineering (General), Visualization}, isbn = {9783540332640}, author = {De Floriani, Leila and Spagnuolo,Michela} } @conference {11985, title = {Multiple View Image Reconstruction: A Harmonic Approach}, booktitle = {IEEE Conference on Computer Vision and Pattern Recognition, 2007. CVPR {\textquoteright}07}, year = {2007}, month = {2007/06/17/22}, pages = {1 - 8}, publisher = {IEEE}, organization = {IEEE}, abstract = {This paper presents a new constraint connecting the signals in multiple views of a surface. The constraint arises from a harmonic analysis of the geometry of the imaging process and it gives rise to a new technique for multiple view image reconstruction. Given several views of a surface from different positions, fundamentally different information is present in each image, owing to the fact that cameras measure the incoming light only after the application of a low-pass filter. Our analysis shows how the geometry of the imaging is connected to this filtering. This leads to a technique for constructing a single output image containing all the information present in the input images.}, keywords = {CAMERAS, filtering theory, Geometry, Harmonic analysis, Image reconstruction, imaging process geometry, Information filtering, Joining processes, Low pass filters, low-pass filter, low-pass filters, multiple view image reconstruction, Position measurement, Power harmonic filters, surface reconstruction}, isbn = {1-4244-1180-7}, doi = {10.1109/CVPR.2007.383285}, author = {Domke, J. and Aloimonos, J.} } @conference {14187, title = {A Projective Invariant for Textures}, booktitle = {2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition}, volume = {2}, year = {2006}, month = {2006///}, pages = {1932 - 1939}, publisher = {IEEE}, organization = {IEEE}, abstract = {Image texture analysis has received a lot of attention in the past years. Researchers have developed many texture signatures based on texture measurements, for the purpose of uniquely characterizing the texture. Existing texture signatures, in general, are not invariant to 3D transforms such as view-point changes and non-rigid deformations of the texture surface, which is a serious limitation for many applications. In this paper, we introduce a new texture signature, called the multifractal spectrum (MFS). It provides an efficient framework combining global spatial invariance and local robust measurements. The MFS is invariant under the bi-Lipschitz map, which includes view-point changes and non-rigid deformations of the texture surface, as well as local affine illumination changes. Experiments demonstrate that the MFS captures the essential structure of textures with quite low dimension.}, keywords = {Computer science, Computer vision, Educational institutions, Fractals, Geometry, Image texture, Level set, lighting, Robustness, Surface texture}, isbn = {0-7695-2597-0}, doi = {10.1109/CVPR.2006.38}, author = {Yong Xu and Hui Ji and Ferm{\"u}ller, Cornelia} } @conference {14209, title = {Compound eye sensor for 3D ego motion estimation}, booktitle = {2004 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2004. (IROS 2004). Proceedings}, volume = {4}, year = {2004}, month = {2004/10/28/Sept.}, pages = {3712- 3717 vol.4 - 3712- 3717 vol.4}, publisher = {IEEE}, organization = {IEEE}, abstract = {We describe a compound eye vision sensor for 3D ego motion computation. Inspired by eyes of insects, we show that the compound eye sampling geometry is optimal for 3D camera motion estimation. This optimality allows us to estimate the 3D camera motion in a scene-independent and robust manner by utilizing linear equations. The mathematical model of the new sensor can be implemented in analog networks resulting in a compact computational sensor for instantaneous 3D ego motion measurements in full six degrees of freedom.}, keywords = {3D camera motion estimation, CAMERAS, compound eye vision sensor, Computer vision, Equations, Eyes, Geometry, Image sensors, Insects, linear equations, Motion estimation, robot vision, Robustness, sampling geometry, Sampling methods, Sensor phenomena and characterization}, isbn = {0-7803-8463-6}, doi = {10.1109/IROS.2004.1389992}, author = {Neumann, J. and Ferm{\"u}ller, Cornelia and Aloimonos, J. and Brajovic,V.} } @article {12060, title = {Visual space-time geometry - A tool for perception and the imagination}, journal = {Proceedings of the IEEE}, volume = {90}, year = {2002}, month = {2002/07//}, pages = {1113 - 1135}, abstract = {Although the fundamental ideas underlying research efforts in the field of computer vision have not radically changed in the past two decades, there has been a transformation in the way work in this field is conducted. This is primarily due to the emergence of a number of tools, of both a practical and a theoretical nature. One such tool, celebrated throughout the nineties, is the geometry of visual space-time. It is known under a variety of headings, such as multiple view geometry, structure from motion, and model building. It is a mathematical theory relating multiple views (images) of a scene taken at different viewpoints to three-dimensional models of the (possibly dynamic) scene. This mathematical theory gave rise to algorithms that take as input images (or video) and provide as output a model of the scene. Such algorithms are one of the biggest successes of the field and they have many applications in other disciplines, such as graphics (image-based rendering, motion capture) and robotics (navigation). One of the difficulties, however is that the current tools cannot yet be fully automated, and they do not provide very accurate results. More research is required for automation and high precision. During the past few years we have investigated a number of basic questions underlying the structure from motion problem. Our investigations resulted in a small number of principles that characterize the problem. These principles, which give rise to automatic procedures and point to new avenues for studying the next level of the structure from motion problem, are the subject of this paper.}, keywords = {3-D motion estimation, Buildings, Computer vision, Geometry, Graphics, Image sequences, Layout, Mathematical model, mathematical theory, model building, Motion estimation, multiple view geometry, multiple views, Navigation, optical flow, optical illusions, patch correspondence, Rendering (computer graphics), Robotics and automation, Solid modeling, structure from motion, three-dimensional models, visual space-time}, isbn = {0018-9219}, doi = {10.1109/JPROC.2002.801440}, author = {Ferm{\"u}ller, Cornelia and Baker, P. and Aloimonos, J.} }