On Degeneracy of Linear Reconstruction from Three Views: Linear Line Complex and Applications

This paper investigates the linear degeneracies of projective structure estimation from point and line features across three views. We show that the rank of the linear system of equations for recovering the trilinear tensor of three views reduces to 23 (instead of 26) in the case when the scene is a Linear Line Complex (set of lines in space intersecting at a common line) and is 21 when the scene is planar. The LLC situation is only linearly degenerate, and we show that one can obtain a unique solution when the admissibility constraints of the tensor are accounted for. The line configuration described by an LLC, rather than being some obscure case, is in fact quite typical. It includes, as a particular example, the case of a camera moving down a hallway in an office environment or down an urban street. Furthermore, an LLC situation may occur as an artifact such as in direct estimation from spatio-temporal derivatives of image brightness. Therefore, an investigation into degeneracies and their remedy is important also in practice.

Finding Texture Boundaries in Images

Texture provides one cue for identifying the physical cause of an intensity edge, such as occlusion, shadow, surface orientation or reflectance change. Marr, Julesz, and others have proposed that texture is represented by small lines or blobs, called 'textons' by Julesz [1981a], together with their attributes, such as orientation, elongation, and intensity. Psychophysical studies suggest that texture boundaries are perceived where distributions of attributes over neighborhoods of textons differ significantly. However, these studies, which deal with synthetic images, neglect to consider two important questions: How can these textons be extracted from images of natural scenes? And how, exactly, are texture boundaries then found? This thesis proposes answers to these questions by presenting an algorithm for computing blobs from natural images and a statistic for measuring the difference between two sample distributions of blob attributes. As part of the blob detection algorithm, methods for estimating image noise are presented, which are applicable to edge detection as well.

Optimal Unsupervised Learning in Feedforward Neural Networks

We investigate the properties of feedforward neural networks trained with Hebbian learning algorithms. A new unsupervised algorithm is proposed which produces statistically uncorrelated outputs. The algorithm causes the weights of the network to converge to the eigenvectors of the input correlation with largest eigenvalues. The algorithm is closely related to the technique of Self-supervised Backpropagation, as well as other algorithms for unsupervised learning. Applications of the algorithm to texture processing, image coding, and stereo depth edge detection are given. We show that the algorithm can lead to the development of filters qualitatively similar to those found in primate visual cortex.

Learning-Based Approach to Real Time Tracking and Analysis of Faces

This paper describes a trainable system capable of tracking faces and facialsfeatures like eyes and nostrils and estimating basic mouth features such as sdegrees of openness and smile in real time. In developing this system, we have addressed the twin issues of image representation and algorithms for learning. We have used the invariance properties of image representations based on Haar wavelets to robustly capture various facial features. Similarly, unlike previous approaches this system is entirely trained using examples and does not rely on a priori (hand-crafted) models of facial features based on optical flow or facial musculature. The system works in several stages that begin with face detection, followed by localization of facial features and estimation of mouth parameters. Each of these stages is formulated as a problem in supervised learning from examples. We apply the new and robust technique of support vector machines (SVM) for classification in the stage of skin segmentation, face detection and eye detection. Estimation of mouth parameters is modeled as a regression from a sparse subset of coefficients (basis functions) of an overcomplete dictionary of Haar wavelets.

Subcutaneous study on the controlled release of Etanidazole and Taxol for the treatment of Glioma

BALB/c nude mice 6 weeks old were inoculated with glioma C6 cell-line and the efficacy of the different amount of Etanidazole-discs and Taxol-microspheres was investigated. Poly (D,L-lactic-co-glycolic acid) (PLGA) was used as the main encapsulating polymer and polyethylene glycol was added to increase the porosity. The 1% drug loading microspheres of each drug were produced by spray drying and the discs were obtained by compressing the Etanidazole-microspheres. Intra-tumoral injection followed by irradiation resulted in high systemic dosage and thus systemic toxicity. Tumors grown for 6 days, 9 days and 16 days were implanted with 0.5 mg or 1.0 mg or 1.5 mg of the drug. A radiation dosage of 2 Gy each time for a number of times was given for animals implanted with Etanidazole and no irradiation was given for animals implanted with Taxol. Increasing the number of doses clearly decreased the rate of tumor growth. The increase in the amount of drug on smaller sized tumors controlled the tumor better and there was agglomeration of the microspheres resulting in deviation of release profile of the drug as compared to the in vitro studies. It was observed that 1.0 mg of Taxol given to a tumor grown for 6 days was able to suppress the tumor for a total period of approximately two months and no tumor resurrection was observed during the second month.