Invention Grant
US08866936B2 Systems and methods for training an active random field for real-time image denoising
有权
用于训练用于实时图像去噪的主动随机场的系统和方法
- Patent Title: Systems and methods for training an active random field for real-time image denoising
- Patent Title (中): 用于训练用于实时图像去噪的主动随机场的系统和方法
-
Application No.: US12508211Application Date: 2009-07-23
-
Publication No.: US08866936B2Publication Date: 2014-10-21
- Inventor: Adrian Gheorghe Barbu
- Applicant: Adrian Gheorghe Barbu
- Applicant Address: US FL Tallahassee
- Assignee: Florida State University of Research Foundation
- Current Assignee: Florida State University of Research Foundation
- Current Assignee Address: US FL Tallahassee
- Agency: Sutherland Asbill & Brennan LLP
- Main IPC: H04N5/217
- IPC: H04N5/217 ; H04N9/64 ; H04N5/21 ; G06K9/62 ; G06T5/00 ; G06K9/40 ; H04N5/357 ; G06T5/20
Abstract:
An Active Random Field is presented, in which a Markov Random Field (MRF) or a Conditional Random Field (CRF) is trained together with a fast inference algorithm using pairs of input and desired output and a benchmark error measure.
Public/Granted literature
- US20100020208A1 SYSTEMS AND METHODS FOR TRAINING AN ACTIVE RANDOM FIELD FOR REAL-TIME IMAGE DENOISING Public/Granted day:2010-01-28
Information query
