TY - JOUR T1 - A Blur-robust Descriptor with Applications to Face Recognition JF - IEEE Transactions on Pattern Analysis and Machine Intelligence Y1 - 2012 A1 - Gopalan,R. A1 - Taheri, S. A1 - Turaga,P. A1 - Chellapa, Rama KW - Blur KW - convolution KW - Face KW - face recognition KW - Grassmann manifold KW - Kernel KW - Manifolds KW - NOISE KW - PROBES AB - Understanding the effect of blur is an important problem in unconstrained visual analysis. We address this problem in the context of image-based recognition, by a fusion of image-formation models, and differential geometric tools. First, we discuss the space spanned by blurred versions of an image and then under certain assumptions, provide a differential geometric analysis of that space. More specifically, we create a subspace resulting from convolution of an image with a complete set of orthonormal basis functions of a pre-specified maximum size (that can represent an arbitrary blur kernel within that size), and show that the corresponding subspaces created from a clean image and its blurred versions are equal under the ideal case of zero noise, and some assumptions on the properties of blur kernels. We then study the practical utility of this subspace representation for the problem of direct recognition of blurred faces, by viewing the subspaces as points on the Grassmann manifold and present methods to perform recognition for cases where the blur is both homogenous and spatially varying. We empirically analyze the effect of noise, as well as the presence of other facial variations between the gallery and probe images, and provide comparisons with existing approaches on standard datasets. VL - PP SN - 0162-8828 CP - 99 M3 - 10.1109/TPAMI.2012.15 ER - TY - CONF T1 - Domain adaptation for object recognition: An unsupervised approach T2 - 2011 IEEE International Conference on Computer Vision (ICCV) Y1 - 2011 A1 - Gopalan,R. A1 - Ruonan Li A1 - Chellapa, Rama KW - Data models KW - data representations KW - discriminative classifier KW - Feature extraction KW - Grassmann manifold KW - image sampling KW - incremental learning KW - labeled source domain KW - Manifolds KW - measurement KW - object category KW - Object recognition KW - Principal component analysis KW - sampling points KW - semisupervised adaptation KW - target domain KW - underlying domain shift KW - unsupervised approach KW - unsupervised domain adaptation KW - Unsupervised learning KW - vectors AB - Adapting the classifier trained on a source domain to recognize instances from a new target domain is an important problem that is receiving recent attention. In this paper, we present one of the first studies on unsupervised domain adaptation in the context of object recognition, where we have labeled data only from the source domain (and therefore do not have correspondences between object categories across domains). Motivated by incremental learning, we create intermediate representations of data between the two domains by viewing the generative subspaces (of same dimension) created from these domains as points on the Grassmann manifold, and sampling points along the geodesic between them to obtain subspaces that provide a meaningful description of the underlying domain shift. We then obtain the projections of labeled source domain data onto these subspaces, from which a discriminative classifier is learnt to classify projected data from the target domain. We discuss extensions of our approach for semi-supervised adaptation, and for cases with multiple source and target domains, and report competitive results on standard datasets. JA - 2011 IEEE International Conference on Computer Vision (ICCV) PB - IEEE SN - 978-1-4577-1101-5 M3 - 10.1109/ICCV.2011.6126344 ER - TY - CONF T1 - Nearest-neighbor search algorithms on non-Euclidean manifolds for computer vision applications T2 - Proceedings of the Seventh Indian Conference on Computer Vision, Graphics and Image Processing Y1 - 2010 A1 - Turaga,Pavan A1 - Chellapa, Rama KW - Grassmann manifold KW - hashing KW - manifold KW - nearest-neighbor KW - region covariance KW - shapes AB - Nearest-neighbor searching is a crucial component in many computer vision applications such as face recognition, object recognition, texture classification, and activity recognition. When large databases are involved in these applications, it is also important to perform these searches in a fast manner. Depending on the problem at hand, nearest neighbor strategies need to be devised over feature and model spaces which in many cases are not Euclidean in nature. Thus, metrics that are tuned to the geometry of this space are required which are also known as geodesics. In this paper, we address the problem of fast nearest neighbor searching in non-Euclidean spaces, where in addition to dealing with the large size of the dataset, the significant computational load involves geodesic computations. We study the applicability of the various classes of nearest neighbor algorithms toward this end. Exact nearest neighbor methods that rely solely on the existence of a metric can be extended, albeit with a huge computational cost. We derive an approximate method of searching via approximate embeddings using the logarithmic map. We study the error incurred in such an embedding and show that it performs well in real experiments. JA - Proceedings of the Seventh Indian Conference on Computer Vision, Graphics and Image Processing T3 - ICVGIP '10 PB - ACM CY - New York, NY, USA SN - 978-1-4503-0060-5 UR - http://doi.acm.org/10.1145/1924559.1924597 M3 - 10.1145/1924559.1924597 ER - TY - CONF T1 - The role of geometry in age estimation T2 - 2010 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP) Y1 - 2010 A1 - Turaga,P. A1 - Biswas,S. A1 - Chellapa, Rama KW - age estimation KW - Aging KW - Biometrics KW - computational geometry KW - Face KW - Face Geometry KW - Facial animation KW - Feature extraction KW - function estimation problem KW - geometric face attributes KW - Geometry KW - Grassmann manifold KW - human face modeling KW - human face understanding KW - HUMANS KW - Mouth KW - regression KW - Regression analysis KW - SHAPE KW - Solid modeling KW - solid modelling KW - velocity vector AB - 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. JA - 2010 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP) PB - IEEE SN - 978-1-4244-4295-9 M3 - 10.1109/ICASSP.2010.5495292 ER -