Linear Object Classes and Image Synthesis from a Single Example Image

The need to generate new views of a 3D object from a single real image arises in several fields, including graphics and object recognition. While the traditional approach relies on the use of 3D models, we have recently introduced techniques that are applicable under restricted conditions but simpler. The approach exploits image transformations that are specific to the relevant object class and learnable from example views of other "prototypical" objects of the same class. In this paper, we introduce such a new technique by extending the notion of linear class first proposed by Poggio and Vetter. For linear object classes it is shown that linear transformations can be learned exactly from a basis set of 2D prototypical views. We demonstrate the approach on artificial objects and then show preliminary evidence that the technique can effectively "rotate" high- resolution face images from a single 2D view.

Using hybrid knowledge engineering and image processing in color virtual restoration of ancient murals

IEEE Transactions on Knowledge and Data Engineering, vol. 15, no. 5, pp. 1338-1343, 2003.

Isoperimetric Graph Partitioning for Data Clustering and Image Segmentation

Spectral methods of graph partitioning have been shown to provide a powerful approach to the image segmentation problem. In this paper, we adopt a different approach, based on estimating the isoperimetric constant of an image graph. Our algorithm produces the high quality segmentations and data clustering of spectral methods, but with improved speed and stability.

The What-And-Where Filter: A Spatial Mapping Neural Network for Object Recognition and Image Understanding

The What-and-Where filter forms part of a neural network architecture for spatial mapping, object recognition, and image understanding. The Where fllter responds to an image figure that has been separated from its background. It generates a spatial map whose cell activations simultaneously represent the position, orientation, ancl size of all tbe figures in a scene (where they are). This spatial map may he used to direct spatially localized attention to these image features. A multiscale array of oriented detectors, followed by competitve and interpolative interactions between position, orientation, and size scales, is used to define the Where filter. This analysis discloses several issues that need to be dealt with by a spatial mapping system that is based upon oriented filters, such as the role of cliff filters with and without normalization, the double peak problem of maximum orientation across size scale, and the different self-similar interpolation properties across orientation than across size scale. Several computationally efficient Where filters are proposed. The Where filter rnay be used for parallel transformation of multiple image figures into invariant representations that are insensitive to the figures' original position, orientation, and size. These invariant figural representations form part of a system devoted to attentive object learning and recognition (what it is). Unlike some alternative models where serial search for a target occurs, a What and Where representation can he used to rapidly search in parallel for a desired target in a scene. Such a representation can also be used to learn multidimensional representations of objects and their spatial relationships for purposes of image understanding. The What-and-Where filter is inspired by neurobiological data showing that a Where processing stream in the cerebral cortex is used for attentive spatial localization and orientation, whereas a What processing stream is used for attentive object learning and recognition.

On the problems of object restoration and image extrapolation in optics

In this paper we consider the problems of object restoration and image extrapolation, according to the regularization theory of improperly posed problems. In order to take into account the stochastic nature of the noise and to introduce the main concepts of information theory, great attention is devoted to the probabilistic methods of regularization. The kind of the restored continuity is investigated in detail; in particular we prove that, while the image extrapolation presents a Hölder type stability, the object restoration has only a logarithmic continuity. © 1979 American Institute of Physics.

RELATIONSHIP BETWEEN WORD AND BIT LEVEL SYSTOLIC ARRAYS AS APPLIED TO MATRIX multiplied by MATRIX MULTIPLICATIONS.

The mapping of matrix multiplied by matrix multiplication onto both word and bit level systolic arrays has been investigated. It has been found that well defined word and bit level data flow constraints must be satisfied within such circuits. An efficient and highly regular bit level array has been generated by exploiting the basic compatibilities in data flow symmetries at each level of the problem. A description of the circuit which emerges is given and some details relating to its practical implementation are discussed.

BIT-LEVEL SYSTOLIC ARRAYS FOR SIGNAL AND IMAGE PROCESSING.

This paper describes the design and the architecture of a bit-level systolic array processor. The bit-level systolic array described is directly applicable to a wide range of image processing operations where high performance and throughput are essential. The architecture is illustrated by describing the operation of the correlator and convolver chips which are being developed. The advantage of the system is also discussed.

Detection of changes of the optic disc in glaucomatous eyes:Clinical examination and image analysis with the Topcon Imagenet system

Purpose: This study was designed to evaluate the clinical agreement in the detection of optic disc changes and the ability of computerized image analysis to detect glaucomatous deterioration of the optic disc. Methods: Pairs of stereophotographs of 35 glaucomatous optic discs taken 5 years apart and of 5 glaucomatous discs photographed twice on the same day. Two glaucoma specialists examined the pairs of stereophotographs (35 cases and 5 controls) in a masked manner and judged whether the optic disc showed changes in the optic disc compatible with progression of glaucomatous damage. The stereophotographs of the five optic discs photographed twice on the same day (which by definition did not change) and of five cases judged to have deteriorated by both glaucoma specialists were analyzed by computerized image analysis with the Topcon ImageNet system. Intra- and inter-observer agreement in the detection of optic disc changes (evaluated using kappa statistic), and changes in the rim area to disc area ratio (evaluated using descriptive statistics and paired t-test). Results: Intra-observer agreement had a kappa value of 0.75 for observer 1 and 0.60 for the observer 2. Inter-observer agreement between the glaucoma specialists had a kappa value of 0.60. The image analyzer did not discriminate between controls and cases with clinically apparent glaucomatous change of the optic disc. Conclusion: Clinical agreement in detecting changes in the optic disc was moderate to substantial. Computerized image analysis with the Topcon ImageNet system appeared not to be useful in detecting glaucomatous changes of the optic disc.