Open Access. Powered by Scholars. Published by Universities.®

Physical Sciences and Mathematics Commons™

Open Access. Powered by Scholars. Published by Universities.®

Computer Sciences

Selected Works

2006

Articles 31 - 40 of 40

Full-Text Articles in Physical Sciences and Mathematics

Data Driven Image Models Through Continuous Joint Alignment, Erik G. Learned-Miller Dec 2005

Data Driven Image Models Through Continuous Joint Alignment, Erik G. Learned-Miller

Erik G Learned-Miller

This paper presents a family of techniques that we call congealing for modeling image classes from data. The idea is to start with a set of images and make them appear as similar as possible by removing variability along the known axes of variation. This technique can be used to eliminate "nuisance” variables such as affine deformations from handwritten digits or unwanted bias fields from magnetic resonance images. In addition to separating and modeling the latent images—i.e., the images without the nuisance variables—we can model the nuisance variables themselves, leading to factorized generative image models. When nuisance variable distributions are …

Go to article

A Hierarchical, Hmmbased Automatic Evaluation Of Ocr Accuracy For A Digital Library Of Books, Shaolei Feng, R. Manmatha Dec 2005

A Hierarchical, Hmmbased Automatic Evaluation Of Ocr Accuracy For A Digital Library Of Books, Shaolei Feng, R. Manmatha

R. Manmatha

A number of projects are creating searchable digital libraries of printed books. These include the Million Book Project, the Google Book project and similar efforts from Yahoo and Microsoft. Content-based on line book retrieval usually requires first converting printed text into machine readable (e.g. ASCII) text using an optical character recognition (OCR) engine and then doing full text search on the results. Many of these books are old and there are a variety of processing steps that are required to create an end to end system. Changing any step (including the scanning process) can affect OCR performance and hence a …

Go to article

Joint Feature Selection For Object Detection And Recognition, Jerod J. Weinman, Allen Hanson, Erik G. Learned-Miller Dec 2005

Joint Feature Selection For Object Detection And Recognition, Jerod J. Weinman, Allen Hanson, Erik G. Learned-Miller

Erik G Learned-Miller

Object detection and recognition systems, such as face detectors and face recognizers, are often trained separately and operated in a feed-forward fashion. Selecting a small number of features for these tasks is important to prevent over-fitting and reduce computation. However, when a system has such related or sequential tasks, selecting features for these tasks independently may not be optimal. We propose a framework for choosing features to be shared between object detection and recognition tasks. The result is a system that achieves better performance by joint training and is faster because some features for identification have already been computed for …

Go to article

Economics Of Information Security Investment In The Case Of Simultaneous Attacks, C. Derrick Huang, Qing Hu, Ravi S. Behara Dec 2005

Economics Of Information Security Investment In The Case Of Simultaneous Attacks, C. Derrick Huang, Qing Hu, Ravi S. Behara

Qing Hu

With billions of dollars being spent on information security related products and services each year, the economics of information security investment has become an important area of research, with significant implications for management practices. Drawing on recent studies that examine optimal security investment levels under various attack scenarios, we propose an economic model that considers simultaneous attacks from multiple external agents with distinct characteristics, and derive optimal investments based on the principle of benefit maximization. The relationships among the major variables, such as systems vulnerability, security breach probability, potential loss of security breach, and security investment levels, are investigated via …

Go to article

Discriminative Training Of Hyper-Feature Models For Object Identification, Vidit Jain, Erik G. Learned-Miller Dec 2005

Discriminative Training Of Hyper-Feature Models For Object Identification, Vidit Jain, Erik G. Learned-Miller

Erik G Learned-Miller

Object identification is the task of identifying specific objects belonging to the same class such as cars. We often need to recognize an object that we have only seen a few times. In fact, we often observe only one example of a particular object before we need to recognize it again. Thus we are interested in building a system which can learn to extract distinctive markers from a single example and which can then be used to identify the object in another image as “same ” or “different”. Previous work by Ferencz et al. introduced the notion of hyper-features, which …

Go to article

A Mobile Agents-Based Approach To Test The Reliability Of Web Services, Jia Zhang Dec 2005

A Mobile Agents-Based Approach To Test The Reliability Of Web Services, Jia Zhang

Jia Zhang

The paradigm of web services has been transforming the internet from a repository of data into a repository of services, or so-called web services. As more and more web services are published on the internet, how to opt for an appropriate and trustworthy web service poses a big challenge. In this paper we propose a mobile agents-based approach that selects reliable web service components in a cost-effective manner.

Go to article

Neural Basis Of Dyslexia: A Comparison Between Dyslexic And Non-Dyslexic Children Equated For Reading Ability, Fumiko Hoeft, Arvel Hernandez, Glenn Mcmillon, Heather Taylor-Hill, Jennifer L. Martindale, Ann Meyler, Timothy A. Keller, Wai Ting Siok, Gayle K. Deutsch, Marcel Adam Just, Susan Whitfield-Gabrieli, John D. E. Gabrieli Dec 2005

Neural Basis Of Dyslexia: A Comparison Between Dyslexic And Non-Dyslexic Children Equated For Reading Ability, Fumiko Hoeft, Arvel Hernandez, Glenn Mcmillon, Heather Taylor-Hill, Jennifer L. Martindale, Ann Meyler, Timothy A. Keller, Wai Ting Siok, Gayle K. Deutsch, Marcel Adam Just, Susan Whitfield-Gabrieli, John D. E. Gabrieli

Marcel Adam Just

No abstract provided.

Go to article

Improving Recognition Of Novel Input With Similarity, Jerod J. Weinman, Erik G. Learned-Miller Dec 2005

Improving Recognition Of Novel Input With Similarity, Jerod J. Weinman, Erik G. Learned-Miller

Erik G Learned-Miller

Many sources of information relevant to computer vision and machine learning tasks are often underused. One example is the similarity between the elements from a novel source, such as a speaker, writer, or printed font. By comparing instances emitted by a source, we help ensure that similar instances are given the same label. Previous approaches have clustered instances prior to recognition. We propose a probabilistic framework that unifies similarity with prior identity and contextual information. By fusing information sources in a single model, we eliminate unrecoverable errors that result from processing the information in separate stages and improve overall accuracy. …

Go to article

Survey Of Computer Supported Business Collaboration In Support Of Business Processes, Carl K. Chang, Jia Zhang, Kai H. Chang Dec 2005

Survey Of Computer Supported Business Collaboration In Support Of Business Processes, Carl K. Chang, Jia Zhang, Kai H. Chang

Jia Zhang

No abstract provided.

Go to article

Controlled Generation Of Hard And Easy Bayesian Networks: Impact On Maximal Clique Size In Tree Clustering, Ole J. Mengshoel, David C. Wilkins, Dan Roth Dec 2005

Controlled Generation Of Hard And Easy Bayesian Networks: Impact On Maximal Clique Size In Tree Clustering, Ole J. Mengshoel, David C. Wilkins, Dan Roth

Ole J Mengshoel

This article presents and analyzes algorithms that systematically generate random Bayesian networks of varying difficulty levels, with respect to inference using tree clustering. The results are relevant to research on efficient Bayesian network inference, such as computing a most probable explanation or belief updating, since they allow controlled experimentation to determine the impact of improvements to inference algorithms. The results are also relevant to research on machine learning of Bayesian networks, since they support controlled generation of a large number of data sets at a given difficulty level. Our generation algorithms, called BPART and MPART, support controlled but random construction …

Go to article

First Prev