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

Intelligent electronic vote analyzing and locating method capable of resisting image stretching shift

A technology of intelligent analysis and image stretching, applied in the directions of instruments, character and pattern recognition, computer parts, etc., can solve the problems of image stretching and offset, the failure of positioning the ballot identification frame area, affecting the voting and counting work, etc.

Active Publication Date: 2017-09-22
广东清华文通科技有限公司
View PDF10 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this kind of intelligent electronic ballot recognition technology, because when the scanner scans the ballot, sometimes the scanned image will be stretched and shifted. If the stretched and offset image is used for positioning and recognition, the positioning of the stretched part of the ballot recognition frame area will fail, causing the scanned ballot image to become invalid, which will affect the vote counting work

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
  • Intelligent electronic vote analyzing and locating method capable of resisting image stretching shift
  • Intelligent electronic vote analyzing and locating method capable of resisting image stretching shift
  • Intelligent electronic vote analyzing and locating method capable of resisting image stretching shift

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0015] Such as figure 1 , the "+" symbols in the upper left corner, upper right corner and lower left corner in the figure are the positioning marks of electronic ballots. In the figure, the principles of the present invention are illustrated by taking the basic ballot identification frame area 1, area 2, and area 3 at the mark as examples.

[0016] Set the basic ballot identification frame area 1, area 2, and area 3. If the coordinates are: area 1 (280, 380, 70, 60), area 2 (352, 380, 70, 60), area 3 (424, 380, 70, 60) Among them, the line width pixel is 2.

[0017] Assuming that the electronic ballot image scanned by the scanner is stretched, causing the coordinate x of area 1 to shift by 25 pixels and y by 15 pixels, then the real coordinates of area 1 on the scanned electronic ballot image should be (305, 395, 70, 60),

[0018] Computer software for positioning recognition steps:

[0019] 1. The coordinates of the computer software’s first positioning and recognition s...

Embodiment 2

[0026] Such as figure 2 ., The difference from Embodiment 1 is that the positioning mark of the electronic ballot is the outer frame a of the ballot content on the electronic ballot. In this case, the identification process of the electronic ballot positioning mark, that is, the real coordinates of the ballot content frame a on the electronic ballot is the same as the identification process of the ballot identification frame area, and will not be repeated here. After identifying the real coordinates of the ballot content frame a on the electronic ballot, compare and calculate with the coordinates of the ballot content frame a on the electronic ballot basic template, and then calculate the offset of the ballot content frame a on the electronic ballot quantity.

Embodiment 3

[0028] Such as image 3 , the difference from Embodiment 1 and Embodiment 2 is that the positioning mark of the electronic ballot is the outer frame b of the ballot content on the electronic ballot, and each basic ballot identification frame area is independent of each other. In this case, it is not necessary to calculate the positioning mark of the electronic ballot, that is, the offset of the outer frame b of the ballot content on the electronic ballot, and in the ballot identification frame area identification step, the coordinates of the first identification step of the area to be identified are the electronic ballot The coordinates of the corresponding base ballot recognition frame area on the base template.

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 provides an intelligent electronic vote analyzing and locating method capable of resisting image stretching shift. Thereby, the electronic vote identification accuracy rate can be greatly increased. The working principle of the method is as follows: computer software finally finds out a vote identification box area, which shifts due to image stretching, by successively expanding the locating range of an identification area; the software judges and finds out the vote identification box area by the following conditions: an upper sideline, a lower sideline, a left sideline and a right sideline are found in an area to be identified; and furthermore, the upper sideline, the lower sideline, the left sideline and the right sideline form a continuous rectangle; and, for a condition that a basal vote identification box is in continuous array arrangement, a locating and identifying step of a next area to be identified is as follows: the vote identification box area confirmed and found in the previous identification area is used as the reference; and thus, the vote identification box area corresponding to the identification area can be found more rapidly and accurately.

Description

technical field [0001] The invention relates to the technical field of intelligent electronic ballot recognition, in particular to a method for intelligently analyzing and locating electronic ballots that can resist image stretching and offset. Background technique [0002] At present, in the field of intelligent electronic ballot recognition technology, most of the recognition of electronic ballots still adopts the traditional answer sheet recognition technology. Arranged with black squares, not only the ballots are not beautiful, but also the voters must spend a long time to blacken the ballot identification boxes one by one, which increases the voting time of the voters and causes various inconveniences. With the development of technology, an intelligent electronic ballot recognition technology that does not need to be blacked out has emerged as the times require. Due to the use of pixel intelligent recognition technology, the ballot recognition frame can be in various fo...

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): G06K9/20
CPCG06V10/22
Inventor 方志雄严洪升朱钊李富丹练树挺
Owner 广东清华文通科技有限公司