Jihong Chen

Learn More
A multiscale coder for curves and boundaries is presented. It utilizes a multiscale structure--beamlets--that is designed primarily for linear and curvilinear features. The coder is composed of three main components: 1) a rate-distortion optimized beamlet-based representation, 2) a tree-based coding from a beamlet representation to a symbol stream, and 3)(More)
In target recognition applications of discriminant or classification analysis, each 'feature' is a result of a convolution of an imagery with a filter, which may be derived from a feature vector. It is important to use relatively few features. We analyze an optimal reduced-rank classifier under the two-class situation. Assuming each population is Gaussian(More)
Dimensionality reduction has important applications in exploratory data analysis. A method based on Local Linear Projection (LLP) is proposed. The advantage of this method is that it is robust against uncertainty. Statistical analysis is applied to estimate parameters. Simulational results on synthetic data are promising. Some preliminary experiment of(More)
We investigate an e-commerce stages of growth model in a cross-cultural business context for small Chinese firms in New Zealand. Research findings from 14 case studies show that the Chinese owners/managers of these small firms have a high power distance, and their attitude toward e-commerce technology directly influences their firms' e-commerce growth(More)
Detection is a fundamental problem in many applications. In many cases, knowing the presence of underlying objects is of significant importance. Mul-tiscale methods have been demonstrated to be advantageous in solving this problem. Besides theoretical results that have been achieved, this paper discusses how the 'most powerful' detection can be realized,(More)
Taking advantage of the new developments in mathematical statistics, a multiscale approach is designed to detect filament or filament-like features in noisy images. The major contribution is to introduce a general framework in cases when the data is digital. Our detection method can detect the presence of an underlying curvilinear feature with the lowest(More)
Beamlets are combined with zero-tree coding algorithm to create a new coding method, particularly suitable for lines and curves. Beamlets are a mul-tiscale collection of line segments at a range of scales, location, having a variety of lengths and orientations. The new coding scheme—named JBEAM—is more efficient—in terms of bit rates—in coding binary curvy(More)
What follows is a list of attendees from the 2000 Electronic Materials Conference, which was held June 21-23, 2000 in Denver, Colorado. This list provides the names and company affiliations of attendees. If additional information is required, it will be necessary request it from the TMS Meetings Department (mtgserv@tms.org).