Unlock instant, AI-driven research and patent intelligence for your innovation.

Hand writing identifying method and system

A handwriting recognition and handwriting input technology, applied in character and pattern recognition, instruments, computing, etc., can solve problems such as distortion, difficulty in accurate electronic recognition of characters, etc.

Inactive Publication Date: 2010-05-05
GOOGLE TECHNOLOGY HOLDINGS LLC
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

If nothing else, characters written on such touchpads can easily include a large amount of distortion in character shape, especially for more complex ideographic characters, such as many Chinese and Japanese characters
Therefore, accurate electronic recognition of characters written on such touchpads is especially difficult

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
  • Hand writing identifying method and system
  • Hand writing identifying method and system
  • Hand writing identifying method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] see figure 1 , the flowchart illustrates a handwriting recognition method 100 for determining matching model character candidates that best match a representation of a handwritten input character, according to one embodiment of the present invention. Method 100 begins at step 105, where a representation of a handwritten input character is received. In step 110 the input characters are preprocessed and in step 115 the disorder function D(S) related to the order of the strokes used to create the input characters is calculated. At step 120, the input characters are pre-classified to create a first short list of matching candidate characters. Then in step 125 the directional feature vector is extracted from the input character. At step 130, the directional feature vector is compared to model characters corresponding to the first short list of matching candidate characters to create a second short list of matching candidate characters and an associated first confidence sco...

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

The present invention disclosed a method for identifying hand-written characters and its system. Said method includes the following steps: receiving hand-written inputted character written on the user's interface of electronic equipment; then extracting directional characteristic vector and stroke segment characteristic vector from the described inputted character, finally comparing the above-mentioned two vectors with model character so as to define matched candidate character.

Description

technical field [0001] The present invention generally relates to handwriting recognition processing. The invention is particularly applicable (but not necessarily limited) to the recognition of handwritten ideographic characters. Background technique [0002] For decades, computer recognition of printed text has faced vexing technical problems. Many optical character recognition (OCR) technologies have only recently been improved to recognize scanned text documents with high accuracy. But such OCR techniques are generally only capable of converting text printed by typewriters or electronic printers. Computer recognition of handwritten characters remains a very difficult technical challenge. [0003] Existing methods for recognizing handwritten characters typically include high-resolution templates that capture the temporal dimension associated with the manipulation of written text, in addition to the two physical dimensions of written text. Such stencils are often creat...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/80G06K9/46
Inventor 镇立新葛勇黄建成
Owner GOOGLE TECHNOLOGY HOLDINGS LLC