Template-based intelligent question image acquisition and processing method and system thereof

A technology for image acquisition and processing and questioning, which is applied in character and pattern recognition, instruments, computer components, etc., can solve the problems of deviation of text positioning results, unsatisfactory results, and low text recognition rate, so as to avoid errors in judging papers or missed judgment, reduce calculation running time, and improve the effect of accuracy

Inactive Publication Date: 2017-12-15
宁波梅山保税港区立思辰投资管理有限公司
View PDF9 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] OCR technology is now more and more applied to devices such as mobile smart terminals and PDAs with image scanning (or camera) functions. There are certain technical difficulties that cause deviations in the results of text positioning, and the characters to be recognized cannot be detected conveniently and accurately, or a text area is mistakenly divided into multiple related text sub-areas, which affects the continuity of OCR recognition results. and computational overhead, coupled with the low text recognition rate, resulting in unsatisfactory final results, so at this time, some auxiliary positioning methods are needed to improve text positioning accuracy and recognition accuracy

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
  • Template-based intelligent question image acquisition and processing method and system thereof
  • Template-based intelligent question image acquisition and processing method and system thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0062] Such as figure 1 As shown, a template-based method for intelligent topic image acquisition and processing includes the following steps:

[0063] a. Generate and print out a question sheet template including page number, student information, answer information, identifier, area type and area coordinates, wherein the identifier is located at the upper left, lower right, and lower left positions of the question sheet template;

[0064] b. After completing the answer to the question sheet template, scan or take a photo of the question sheet template to obtain a scanned copy of the answer or a photo of the answer;

[0065] c. Perform graphic processing on the scanned copy of the answer or the photo of the answer to obtain the content information of the picture;

[0066] d, identify the picture content after graphic processing, and judge whether to fully identify the picture content, if yes, then enter step e; if not, then enter step h;

[0067] e, if the identified picture...

Embodiment 2

[0074] In this embodiment, on the basis of Embodiment 1, the step b includes the following steps:

[0075] b1. Turn on taking pictures or scanning to form 3 identification areas corresponding to the 3 identifiers on the question sheet template;

[0076] b2. Judging whether the three identifiers are recognized, if yes, then determine that the center point of the three identifiers corresponds to the position of the question sheet template, and enter step b3; if not, then re-enter step b1;

[0077] b3. After taking pictures or scanning, obtain a scanned copy of the answer or a photo of the answer with student information, question sheet information and answer information.

[0078] After taking pictures or scanning, put the 3 identifiers on the question form template into the corresponding recognition area frame, the system will automatically focus and capture an image containing text after recognition, and confirm that the image corresponds to the center point of the three identi...

Embodiment 3

[0080] In this embodiment, on the basis of Embodiment 1, said step c includes the following steps:

[0081] c1. After obtaining the scanned answer or the photo of the answer, perform affine transformation on the scanned answer or the photo according to the original aspect ratio of the question sheet template;

[0082] c2. According to the area type and area coordinates of the recorded answer template, each area of ​​the scanned answer or answer photo is automatically segmented according to the coordinates, and the images of each area after segmentation are obtained;

[0083] c3. Perform tilt correction and image enhancement on the segmented images in each region to obtain processed image content information.

[0084] Graphically process the images collected after taking photos or scanning, first search the image area, perform affine transformation on the collected image according to the original aspect ratio of the question sheet template, and then detect and locate the text a...

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 discloses a template-based intelligent question image acquisition and processing method. A question sheet template is generated; the question sheet template is scanned or photographed so as to acquire an answer scanning copy or an answer photo; graphic processing is performed; if the image content is completely recognized, whether the image content is student information or answer information is judged, or artificial auxiliary processing is performed; as for the student information, the corresponding student is inquired and the student information is recorded; and as for the answer information, paper marking is performed and the paper marking result is recorded. The invention also discloses a template-based intelligent question image acquisition and processing system comprising a template generation module, a question sheet scanning module, a graphic processing module, an image recognition and judgment module, an image content judgment module, a student information recording module, a paper marking result recording module and an artificial processing module. The text area in the image can be effectively and automatically acquired, and the required text area can be obtained through the interaction mode so that the computation time of the system can be reduced and the locating accuracy can be enhanced.

Description

technical field [0001] The invention relates to the fields of image processing and pattern recognition, in particular to a template-based method for collecting and processing intelligent topic images and a system thereof. Background technique [0002] OCR technology is now more and more applied to devices such as mobile smart terminals and PDAs with image scanning (or camera) functions. There are certain technical difficulties that cause deviations in the results of text positioning, and the characters to be recognized cannot be detected conveniently and accurately, or a text area is mistakenly divided into multiple related text sub-areas, which affects the continuity of OCR recognition results. In addition to the low character recognition rate, the final result is not ideal. Therefore, some auxiliary positioning methods are needed to improve the text positioning accuracy and recognition accuracy. [0003] At present, the basic process of existing image (or video) text reco...

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 & AuthorityApplications(China)
IPC IPC(8): G06K9/20G06K9/32
CPCG06V10/225G06V10/245
Inventor林辉
Owner宁波梅山保税港区立思辰投资管理有限公司