Narrow Results

Supercomputers are coming into wider use for generating realistic imagery for commercial animation, special effects, and scientific simulation. The Connection Machine requires a more radical rethinking of rendering algorithms than previous supercomputers since it is not intended to function as a scalar processor. A fascinating mix of changes from conventional approaches is emerging. Some procedures can run virtually unchanged while others must be turned completely inside out. We have confidence in the viability of the Connection Machine as an architecture for high-end computer graphics. For complex scenes resulting in at least tens of thousands of polygons per frame, most steps of the rendering pipeline can make effective use of the massive number of processors available.

Early approaches to massively parallel graphics systems have focused on processor per pixel organizations. We show that a dynamic mix of organizations, including processor per pixel, processor per vertex, and processor per polygon are necessary. Additionally, we note that an apparent consequence of the style of algorithm enforced by the Connection Machine is an enormously increased appetite for memory. We explore standard algorithms for image generation and note the differences that arise in an implementation for the Connetion Machine. We conclude by attempting a comparison of the viability of alternative computing environments for our application.

This paper describes a novel technique (deviation mapping) that generates images with artistic appearances, e.g. spray painted wall, embossment, cashmere painting, etc. Our technique employs a deviation map constructed from a single background image in the image generation process. Instead of recovering the exact geometry from the background image, the deviation map can be regarded as a virtual surface. This virtual surface is then painted with a foreground image and illuminated to generate the final result. Interestingly, the synthesized images exhibit some artistic appearances. Our method is very fast and very simple to implement.

We present the two-stage adaptive metric learning procedure with improved generalization of missing training data for facial signature authentication. The conventional learning models suffer from degraded recognition rates due to poor estimation of decision boundary to classify impostor patterns. The two-stage networks combine multiple image synthesis methods to assume mixture patterns of training classes and facilitate threshold setting of false acceptance/rejection rates. The margin size of a decision boundary is adjusted to input patterns obtained from synthesized images and depends on the choice of the mixing factor. The present method effectively reduces the margin of a class with an improved recognition rate to classify impostor patterns from 82.2% to 98.8%. Furthermore, we examine the margin structure of the mixture distributions by using the Support Vector Machines.

Most current vehicle black boxes provide a bird’s-eye view of 2D type. This viewpoint has a limited viewing angle which makes it difficult to conduct an accident investigation, parking and awareness of space. To solve these problems, we propose the 3D Around View Monitoring (AVM) algorithm using image composition which combines planar and hemispherical projection method. The experimental results indicate that the proposed method overcome the 2D AVM disadvantages and may be useful for accurate accident investigation, autonomous driving system and other system.

Correspondence analysis is gaining increasing importance in the analysis of electron micrographs of macromolecules. Partial or complete reconstitution of images from their factorial representations is introduced as a useful tool in interpreting variational patterns and tracing their physical origin. The value of image reconstitution is demonstrated with two examples, one using a set of model images and the other a set of images of a haemocyanin molecule assembly product.