Method for identifying capital English letter automatically based on fixed strokes of mobile phone

An English alphabet, automatic recognition technology, applied in the field of recognition, can solve the problems of inability to overcome gravity, the influence of motion trajectory calculation, and the inaccurate calculation of the motion trajectory of the three-axis acceleration sensor, and achieve the effects of accurate calculation, zero drift and gravity elimination.

Active Publication Date: 2016-02-03
赵蕴龙
View PDF4 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] However, the three-axis acceleration sensor is not very accurate for the calculation of the motion trajectory, because its own structural characteristics are to use the rebound characteristics of inertia, and the detection time will be slightly delayed compared to the actual time. In the curve and turning type movement, this This kind of delay is more obvious; at the same time, it cannot overcome gravity, and its own zero drift delay and other problems will affect the calculation of motion trajectory, thus affecting the accuracy of mobile phone input

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
  • Method for identifying capital English letter automatically based on fixed strokes of mobile phone
  • Method for identifying capital English letter automatically based on fixed strokes of mobile phone
  • Method for identifying capital English letter automatically based on fixed strokes of mobile phone

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0064] Take the input "A" as an example. The user first turns the screen to face himself vertically to initialize the program. The writing plane is a vertical plane facing the user. The -Y direction is below the writing plane, and the default gravity is obtained: 1g along the -Y direction, and the maximum value of the absolute value of zero drift MaxZ is obtained. Then move the phone upwards, the three-axis acceleration sensor + Y direction will produce a larger value, set it as Ax 0 , since the direction of gravity is opposite to the direction of movement, 1g needs to be added to the obtained result, which is (Ax 0 +1) g, at this time, if the result does not exceed MaxZ, discard the result and resample. Now assume that it exceeds MaxZ, and then it needs to be judged (Ax 0 +1) the size of g, if the value exceeds 5g, the final acceleration result is ln(Ax 0 +1)g, otherwise use (Ax 0 +1) g. Then multiply it by the sampling period t, and add the result to the speed accumulat...

Embodiment 2

[0066] If in Example 1, the input is not accurate, for example, in the upward movement, the user actually moves obliquely to the upper right, then there may be a track to the right detected, and there will be two directions in the buffer: " "Up" and "Right", and then the user continues to move. If the detection of "Up" is more than 80% of the total number of buffer samples, it will still be recognized as Up. If it does not exceed 80% and the number of samples exceeds 500, the system will automatically clear the buffer and recalculate.

Embodiment 3

[0068] If in embodiment 1, there is no pause after changing the direction, the system cannot automatically clear the speed accumulation, and the error accumulation of the result will increase, so after the first new stroke "right" is added to the trajectory chain , the user will continue to input "down". At this time, the number of samples of "down" in the buffer must exceed 85% of the total number of samples in the buffer, and it will be added to the track chain. Continue to input the direction "left" without stopping, exceeding the buffer 87.5% of the total number of samples will be added to the trajectory chain, and so on.

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 invention relates to a method for identifying a capital English letter automatically based on fixed strokes of a mobile phone, which comprises an estimation method of a mobile phone movement track and a matching identification method of the fixed strokes. The method is used for inputting capital English letters and a space key; a user can input the capital English letters in the space through the estimation method of the mobile phone movement track and the matching identification method of the fixed strokes and by using a three-axis acceleration sensor mounted in the mobile phone. The method is applicable for a user with a relatively low visual ability or a circumstance in which a mobile phone keyboard or a touch screen is inconvenient to use; meanwhile, according to the method, a three-axis sensor is corrected, and null shift and gravity are removed, so that the calculation of the mobile phone movement track is more accurate, correct input is accordingly obtained, and the user can write in the space for inputting as using a pen.

Description

technical field [0001] The invention relates to the field of recognition technology, in particular to a method of using a three-axis acceleration sensor in a mobile phone to identify the movement of the mobile phone as an input method for inputting uppercase English characters. Background technique [0002] With the popularity of mobile phones, a large number of input methods suitable for mobile phones have emerged, but the existing mobile phone input methods are all based on mobile phone keyboards or touch screens. If the user's visual ability is low, or the mobile phone keyboard is inconvenient When in use, existing keyboards or touch screens cannot be used for input. [0003] At present, the interaction between people and electronic devices is constantly increasing, and the input methods of electronic devices are no longer limited to specified devices such as keyboards. With the improvement of motion capture, new input methods will continuously improve the ability and co...

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 Applications(China)
IPC IPC(8): G06F3/01G06F3/023
Inventor 赵蕴龙
Owner 赵蕴龙
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap