Supercharge Your Innovation With Domain-Expert AI Agents!

Identification separation and compression of multiple forms with mutants

A form and category technology, applied in character recognition, character and pattern recognition, instruments, etc., can solve problems such as inability to recognize

Inactive Publication Date: 2009-04-29
IBM CORP
View PDF12 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Again, experience has shown that in most systems there is no single template for all form types, but rather several, and there may be unanticipated template variants that cannot be identified by the various forms currently used for form recognition. any combination of global features to identify

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Identification separation and compression of multiple forms with mutants
  • Identification separation and compression of multiple forms with mutants
  • Identification separation and compression of multiple forms with mutants

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] FIG. 1 schematically shows a document image processing system 20 according to a preferred embodiment of the present invention. System 20 includes scanner 22 , or any other type of image capture device known in the art, that receives and scans document 24 . The document 24 contains preprinted forms, which have a template, typically filled in with handwritten, typed or printed characters. The scanner captures an image of the document and transmits the corresponding image data to a form image processor 26, which typically includes a suitable general purpose computer. Alternatively, the image is input into the processor from another source.

[0036] Processor 26 identifies templates in each image it receives and groups the images according to their respective templates. Unlike systems known in the art, processor 26 can sort groups of images with similar but not identical variant templates into subgroups according to the templates of the images using the method described b...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

A method of processing images comprising receiving a set of images having similar characteristics, the set comprising a plurality of classes, wherein each image belongs to one of these classes and contains a fixed portion common to all images in the class to which it belongs (32 , 34, 36) and a variable portion (42) that distinguishes the image from other images in the category. A reference region is found in these images in which the fixed part (44) of the image in the first class is always different from the fixed part (46) of the image in the second class. According to the reference area, the images are divided into categories.

Description

technical field [0001] The present invention relates generally to document image processing and, more particularly, to methods of recognizing preprinted form documents and extracting information filled therein. Background technique [0002] In many document imaging systems, large numbers of forms are scanned into a computer, which then processes the resulting document images to extract relevant information. Typically, these forms consist of preprinted templates with fields that have been filled in by hand or in machine-printed characters. In order to extract the filled information, the computer must first recognize the template. Various image analysis methods are known in the art for these purposes. One such method is described in US Patent No. 5,434,933, the disclosure of which is incorporated herein by reference. [0003] In order to precisely identify the position of the fields in the template, a common technique is for the computer to register each document image with...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06K9/00G06K9/36G06K9/62H04N1/00G06F15/00G06V30/10
CPCG06K9/2054G06K9/00449G06V30/412G06V30/10G06V30/1444G06F18/00
Inventor 阿维亚德·佐特尼克
Owner IBM CORP
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com