projects

Face Relighting, Rotation and Recognition
	This work addresses three primary objectives: Given a few images of a face under varying point source illumination (with cast shadows and specularities), generate images of the face under novel illuminations. Recover the 3D shape of the face and generate images in novel pose and illuminations. Use this capability to generate new images with a face recognition algorithm to build a robust face recognition system. Webpage. [Kumar et al. CVPR 09] [Barmpoutis et al. CVPR 08]
DW-MRI Multi-Fiber Reconstruction and Fiber Tractography
	This work explores different techniques for reconstructing MR signal attenuation from the given DW-MRI data. The reconstructed signal can then be used to detect the local fiber orientations (including fiber crossings) which can be further processes to provide fiber tracks. Each technique is supported by both simulated and real data experiments. Webpage 1. Webpage 2. [Kumar et al. IPMI 09] [Barmpoutis et al IPMI 09] [Barmpoutis et al. NeuroImage 09] [Kumar et al. MMBIA 08] [Barmpoutis et al. MICCAI 08] [Barmpoutis et al. ISBI 08] [Jian et al. IPMI 07] [Jian et al. NeuroImage 07]
Conic Section Classifiers
	We propose a new concept class based on conic sections that is suited for high dimensional sparse data. Each class is assigned a conic section in the input space, described by its focus (point), directrix (hyperplane) and eccentricity (value). Class labels are assigned to data-points based on the eccentricities attributed to them by the class descriptors. The concept class can represent non-linear discriminant boundaries with merely four times the number of parameters as a linear discriminant. Learning involves updating the class descriptors. We also present a tractable learning algorithm for binary classification. For each descriptor, we track its feasible space that results in identical labeling for classified points. We then pick a solution from it to learn misclassified points as well as pursue simpler (near-linear) boundaries. The performance of our classifier is comparable to state-of-the-art and out-performed them on several data sets. Webpage. [Kodipaka et al. CVPR 08] [Banerjee et al. CVPR 06]
Hippocampal Shape Analysis and Epilepsy Diagnosis
	The hypothesis being that the shape asymmetry between the left and the right hippocampus can indicate the hemispheric location of an epileptic focus. The scans of two classes of patients with epilepsy, those with a right and those with a left medial temporal lobe focus (RATL and LATL), as validated by clinical consensus and subsequent surgery, were compared to a set of age and sex matched healthy volunteers using both volume and shape based features. Shape-based features are derived from the displacement field characterizing the non-rigid deformation between the left and right hippocampi of a control or a patient as the case may be. Using the shape-based features, the results show a significant improvement in distinguishing between the controls and the rest (RATL and LATL) vis-a-vis volume-based features. Using a novel feature, namely, the normalized histogram of the 3D displacement field, we also achieved significant improvement over the volume-based feature in classifying the patients as belonging to either of the two classes LATL or RATL respectively. It should be noted that automated identification of hemispherical foci of epilepsy has not been previously reported. [Lord et al. TMI 07][Lord et al. SSVM 07][Lord et al. ICCV 07] [Kodipaka et al. MedIA 07]
Image Segmentation and Registration
	We present continuous mixture models which are spatially varying, adaptive, convolution based approaches for smoothing and segmentation. These new and innovative approaches afford to preserve the complicated local geometries of the boundaries of objects in real scenes without using any prior information. First, we extract the local orientation information using Gabor filters. The orientation information at each lattice point is then represented by a continuous mixture of oriented Gaussians. The continuous mixture representation is cast as the Laplace transform of the mixing density over the space of covariance (positive definite) matrices. This mixing density is assumed to be in a parameterized form, namely, a mixture of Wisharts, whose Laplace transform evaluates to a closed form expression called the Rigaut type function: a scalar-valued function of the parameters of the Wishart distribution. The weights in the mixture are then computed using a sparse deconvolution technique. In the second stage, we construct the convolution kernels for smoothing/segmentation using these weights within the continuous mixture kernel. [Subakan et al. CVPR 08] [Subakan et al. ICCV 07]