This study investigated perceptual biases in spatial judgments as a function of the computergraphics eyepoint elevation, monoscopic or stereoscopic display, and target cube location. The display for this experiments ...
详细信息
A multithreaded processor is a good approach to increase the performance by utilizing coarse grain parallelism. The execution of multiple threads in parallel makes a performance prediction difficult because of a compl...
详细信息
A multithreaded processor is a good approach to increase the performance by utilizing coarse grain parallelism. The execution of multiple threads in parallel makes a performance prediction difficult because of a complicated behavior. Thus instruction-level simulation is necessary for a performance evaluation. In practice, it is very difficult to select optimum configuration of microarchitecture through a simulation of wide variety of candidates because of a long simulation time. This paper presents an evaluation method of microarchitecture for multithreaded processors. The method consists of three steps;first, the characteristics of the application are analyzed, secondly, the candidates of microarchitecture are selected in consideration of the characteristics, lastly, the selected architectures are evaluated through the instruction-level simulation using practical application program. The experimental results using computergraphics application show that the proposed evaluation method of microarchitecture are very effective in order to increase the performance of multithreaded processors.
The importance of digital images has increased and the need for hard- and software tools for creating, archiving, and managing digital images as well for image manipulation and image mensuration. The XLTT software (ex...
详细信息
ISBN:
(纸本)0819416967
The importance of digital images has increased and the need for hard- and software tools for creating, archiving, and managing digital images as well for image manipulation and image mensuration. The XLTT software (expandable light tablet tool) is designed to access medium sized digital images (usually 10 to 50 Megapixels each) and allow image coordinate mensuration with subpixel accuracy. Great efforts were spent on the design of the graphical user interface, which gives access to multiple images at a time and allows simultaneous coordinate mensuration of identical points. XLTT is modeled as a digitizer for convenient image mensuration. Additional functions, like image enhancement, geometric transformation of images, stereo mensuration of image pairs, and image correlation are also available. XLTT was developed using IDLR and C and is implemented on silicon graphics workstations.
Animated computergraphics displays of the visible speech gestures of the human face have a number of potential applications. The paper describes a novel method for their creation by bringing together two statisticall...
详细信息
Animated computergraphics displays of the visible speech gestures of the human face have a number of potential applications. The paper describes a novel method for their creation by bringing together two statistically-based techniques, namely hidden Markov modelling and principal component analysis. The animations are derived from images of a real speaker's face and incorporate all the visible features of the primary articulators, including the lips, teeth and tongue, in a graphical display which does not use an artificial facial model. A pilot 'video speech synthesiser' of this kind has been implemented and tested on spoken digit strings.< >
Digital radiography systems apply various imageprocessing algorithms to the detected raw data to make images look similar to conventional film images. Usually, only a fixed imageprocessing is provided, sometimes sli...
详细信息
Digital radiography systems apply various imageprocessing algorithms to the detected raw data to make images look similar to conventional film images. Usually, only a fixed imageprocessing is provided, sometimes slightly parameterizable. To provide greater flexibility to physicians, researchers, and service personnel, we designed and implemented an interpreted language to ease the definition of the processing pipeline. This simple block-structured language allows the processing to be defined very flexibly in terms of basic imageprocessing primitives. Because of the interpretative nature of the language, the imaging processing can be fully customized on-site to the needs of a particular hospital or physician. This approach also allows different types of imageprocessing to be applied after an image has been taken, e.g. when new information about the illness of the patient becomes known. In practice at the Duke University Medical Center, the flexibility and configurability of the system helped to adapt the system to the particular needs of the site. Certain problems related to the state-of-the-art detector could be compensated in software. A locally developed numerical scatter compensation technique has been integrated.< >
The all-nearest neighbor problem (ANN) is stated as follows: given a set of points in the plane, determine for every point in S, a point that lies closest to it. The ANN problem is central to VLSI design, computer gra...
详细信息
The all-nearest neighbor problem (ANN) is stated as follows: given a set of points in the plane, determine for every point in S, a point that lies closest to it. The ANN problem is central to VLSI design, computergraphics, pattern recognition, and imageprocessing, among others. We propose two time-optimal algorithms to solve the ANN problem for an arbitrary set of points in the plane and also for the special case in which the points are vertices of a convex polygon. Both algorithms run on meshes with multiple broadcasting. We first establish an /spl Omega/(log n) time lower bound for the task of solving an arbitrary n-point instance of the ANN problem, even if the points are the vertices of a convex polygon. This lower bound holds for both the CREW-PRAM and for the mesh with multiple broadcasting. Next, we show that the bound is tight by exhibiting algorithms solving the problem in O(log n) time on a mesh with multiple broadcasting of size n/spl times/n. The first algorithm is for an arbitrary point-set, while the second solves the problem in the special case when the points are the vertices of a convex polygon.< >
The method by searching the error code graph (ECG) to find the optimal morphological filter on binary image is proposed in this paper. The problem to find the optimal solution is reduced to the problem for searching a...
详细信息
ISBN:
(纸本)078031865X
The method by searching the error code graph (ECG) to find the optimal morphological filter on binary image is proposed in this paper. The problem to find the optimal solution is reduced to the problem for searching a minimal path in ECG. Since this graph satisfies some greedy properties, only few nodes need to be traversed and examined in this graph.< >
Multiple instruction execution is a major approach to designing high-performance processors. Superscalar and VLIW processor that utilize instruction level parallelism are usually focused on. On the other hand, the mul...
详细信息
Multiple instruction execution is a major approach to designing high-performance processors. Superscalar and VLIW processor that utilize instruction level parallelism are usually focused on. On the other hand, the multithreaded processor can be expected to achieve a high degree of multiple instruction execution by utilizing coarse grain parallelism. Many computergraphics applications (such as the radiosity method and ray-tracing method) can be optimized by reorganizing the code to take advantage of coarse grain parallelism, but the degree of instruction level parallelism is not sufficient for a superscalar processor. Experimental result using the radiosity method shows that the 4-thread multithreaded processor achieves 2.9 times speedup over single thread, while the 4-issue superscalar processor manages around 1.5 times. By duplicating two kinds of function units, the performance of a multithreaded processor increases to 3.7 times, but the performance of a superscalar processor is saturated at around 1.5 times. Therefore, for computergraphics applications, the multithreaded processor is a better approach than the superscalar processor.< >
Affine transformation of volume, in particular rotation, is important in visualisation. The authors present an approach to data-parallel rotation which ensures an efficient mapping from the object space to a rotated v...
详细信息
Affine transformation of volume, in particular rotation, is important in visualisation. The authors present an approach to data-parallel rotation which ensures an efficient mapping from the object space to a rotated viewing space. While the popular rotation-by-shear approach involves multiple resampling, only one resampling operation is used in the algorithm which ensures faster speed and less degradation. Also, a fast rendering algorithm is proposed for the rendering of volume image. The authors implement their algorithm on a massive parallel SIMD computer Decmpp 1200/sx to show its interactivity and quality advantages.< >
In light of the worldwide all-digital HDTV races and the rapid convergence of telecommunication and CATV networks, the TV service in Taiwan is also positioning for major changes. Some are to improve its image receptio...
详细信息
In light of the worldwide all-digital HDTV races and the rapid convergence of telecommunication and CATV networks, the TV service in Taiwan is also positioning for major changes. Some are to improve its image reception quality, others are information services anticipating the digital convergence of data, image and video, via broadcast TV of CATV. These new TV service systems start from the ghost cancellation system-the cure to multipath artifacts, and move into the integration of videoinfo services-the information to home via terrestrial TV or CATV; and then digital TV broadcast that covers the digital family between the currently available TV and the future HDTV. In the paper, the development strategy and the current progress of these systems are described. In particular, the all-digital HDTV prototype system developed in CCL (computer and Communication Research Labs.) is depicted in detail.< >
暂无评论