A Unified Feature Extraction Architecture

نویسندگان

  • Tino Weinkauf
  • Jan Sahner
  • Holger Theisel
  • Hans-Christian Hege
  • Hans-Peter Seidel
چکیده

We present a unified feature extraction architecture consisting of only three core algorithms that allows to extract and track a rich variety of geometrically defined, local and global features evolving in scalar and vector fields. The architecture builds upon the concepts of Feature Flow Fields and Connectors, which can be implemented using the three core algorithms finding zeros, integrating and intersecting stream objects. We apply our methods to extract and track the topology and vortex core lines both in steady and unsteady flow fields.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

An Architecture for Life-long User Modelling

In this paper, we propose a unified architecture for the creation of life-long user profiles. Our architecture combines different steps required for a user profile, including feature extraction and representation, reasoning, recommendation and presentation. We discuss various issues that arise in the context of life-long profiling.

متن کامل

A Novel Architecture for Detecting Phishing Webpages using Cost-based Feature Selection

Phishing is one of the luring techniques used to exploit personal information. A phishing webpage detection system (PWDS) extracts features to determine whether it is a phishing webpage or not. Selecting appropriate features improves the performance of PWDS. Performance criteria are detection accuracy and system response time. The major time consumed by PWDS arises from feature extraction that ...

متن کامل

Multimedia Feature Extraction in the SAPIR Project

SAPIR is a peer-to-peer multimedia information retrieval system that can index structured and unstructured text, still and moving images, speech, and music. The system’s feature extraction component, which analyzes documents to prepare them for indexing, is implemented using UIMA. It handles compound documents using an architecture of (potentially nested) splitters and mergers within a UIMA agg...

متن کامل

The FOOM Method – Modeling Software Product Lines in Industrial Settings

This paper presents FOOM – Feature-based Object Oriented Modeling and its application to a family of sonar systems. FOOM is a synthesis of the FODA (Feature Oriented Domain Analysis) and Horseshoe models. The Unified Software Development Process (USP) is used as a template for describing the architectural transformation. FOOM focuses on identifying user-driven features throughout a product line...

متن کامل

The FOOM Method – Modeling Software Product Line in Industrial Settings

This paper presents FOOM – Feature-based Object Oriented Modeling and its application to a family of sonar systems. FOOM is a synthesis of the FODA (Feature Oriented Domain Analysis) and Horseshoe models. The Unified Software Development Process (USP) is used as a template for describing the architectural transformation. FOOM focuses on identifying user-driven features throughout a product line...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2006