Invention Grant
US08285074B2 Finding low variance regions in document images for generating image anchor templates for content anchoring, data extraction, and document classification
有权
在文档图像中找到低差异区域，以生成用于内容锚定，数据提取和文档分类的图像锚模板
- Patent Title: Finding low variance regions in document images for generating image anchor templates for content anchoring, data extraction, and document classification
- Patent Title (中): 在文档图像中找到低差异区域，以生成用于内容锚定，数据提取和文档分类的图像锚模板
-
Application No.: US12873657Application Date: 2010-09-01
-
Publication No.: US08285074B2Publication Date: 2012-10-09
- Inventor: Eric Saund , Prateek Sarkar , Alejandro E. Brito , Marshall W. Bern , Francois Ragnet
- Applicant: Eric Saund , Prateek Sarkar , Alejandro E. Brito , Marshall W. Bern , Francois Ragnet
- Applicant Address: US CA Palo Alto US CT Norwalk
- Assignee: Palo Alto Research Center Incorporated,Xerox Corporation
- Current Assignee: Palo Alto Research Center Incorporated,Xerox Corporation
- Current Assignee Address: US CA Palo Alto US CT Norwalk
- Agency: Fay Sharpe LLP
- Main IPC: G06K9/20
- IPC: G06K9/20 ; G06K9/62
Abstract:
Methods of generating image anchor templates from low variance regions of document images of a first class are provided. The methods select a document image from the document images of the first class and align the other document images of the first class to the selected document image. Low variance regions are then determined by comparing the aligned document images and the selected document image and used to generate image anchor templates.
Public/Granted literature
Information query
