An answer sheet scoring and marking system based on image mode

An image pattern and image technology, applied in character and pattern recognition, inductive record carriers, instruments, etc., can solve the problems of reduced recognition rate, waste of manpower and material resources, marking errors, etc., to improve robustness, accuracy, and improvement. The effect of recognition

Active Publication Date: 2019-01-29
JIANGSU QUSU EDUCATION TECH
View PDF9 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the above method has high requirements for the accuracy and accuracy of the detection. For example, the traditional positioning point search is used to identify the answer sheet using the contour search and screening method. In the case of incomplete dot printing, the recognition rate will drop sharply, and a slight deviation will lead to error problems in the marking, which needs to be solved manually, which will not only reduce the efficiency of marking and scoring, but also waste manpower and material resources
[0003] Therefore, it is necessary to provide a scoring and grading system for answer papers that can dynamically increase according to user input, using automatic generation of an answer sheet with an anchor point strategy for each question, and combining image recognition to solve the failure of marking papers caused by printing deformation and missing black corner points problem, the image mode-based answer sheet scoring and marking system that controls the error by improving the recognition accuracy has become a technical problem to be solved urgently by those skilled in the art

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
  • An answer sheet scoring and marking system based on image mode
  • An answer sheet scoring and marking system based on image mode
  • An answer sheet scoring and marking system based on image mode

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0076] Please refer to figure 2 and, figure 2 It is a schematic diagram of an image-based answer sheet scoring and marking system provided by an embodiment of the present invention. image 3 It is a schematic structural diagram of an answer sheet in an embodiment of the present invention. The system for scoring and marking an answer sheet based on an image mode provided in this embodiment includes:

[0077] The image acquisition module 41, the image acquisition module 41 installs the driver and connects the scanner by the computer terminal, and scans the answer sheet by the scanner to generate the answer sheet image preservation (such as image 3 shown);

[0078] The two-dimensional code detection module 42, the two-dimensional code detection module 42 forms a cascaded detection model by using the binarization algorithm and HAAR+adaboost training, and completes the two-dimensional code 421 on the answer sheet image and the inside of the two-dimensional code 421 through the...

Embodiment 2

[0087] Please refer to image 3 and Figure 4 , Figure 4 It is a work flow diagram of an image mode-based answer sheet scoring and marking system provided by an embodiment of the present invention. The image mode-based answer sheet scoring and marking system in this embodiment includes the following working steps:

[0088] Step 101, obtain the answer sheet image, install the driver through the computer terminal and connect the scanner, the scanner scans the answer sheet and generates an image for saving;

[0089] Step 102, detect the two-dimensional code, and use the binarization algorithm and the HAAR+adaboost training method to complete the detection of the two-dimensional code on the image of the answer sheet and the three fonts inside the two-dimensional code;

[0090] Step 103, identifying the two-dimensional code, using the open source library ZXING as a decoding tool, intercepting the three back characters detected in the above steps and directly assigning them to th...

Embodiment 3

[0096] Please continue to refer image 3 and Figure 4 , the workflow of the image-based answer sheet giving points and marking system in the present embodiment includes the following steps:

[0097]Obtain the answer sheet image, install the driver through the computer terminal and connect the scanner, the scanner scans the answer sheet and generates an image to save;

[0098] Next step: detect the QR code;

[0099] which, specifically, refer to Figure 5 , Figure 5 It is a flow chart of the training process for detecting a two-dimensional code by a two-dimensional code detection module provided in an embodiment of the present invention. The training process for detecting a two-dimensional code detection model is as follows:

[0100] Step 2021: Collect at least 20,000 (can be 20,000) images, intercept the QR code area and normalize it to a size of 20×20 pixels, and use it as a positive sample image;

[0101] Step 2022: Collect at least 20,000 (above 20,000) images and re...

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 an answer sheet scoring and marking system based on an image mode, comprising an image acquisition module, a two-dimensional code detection module, a two-dimensional code identification module and a positioning point determination module, wherein the positioning points comprises a first positioning point and a second positioning point; a position judging module, a unified dividing module used for uniformly dividing the multiple-choice questions, filling in the blanks and solving the questions on the answer sheet. The answer sheet scoring and marking system based on image mode of the invention can dynamically increase according to user input, using the strategy of automatic generation of anchor points for each question, combined with image recognition to solve the problem of test paper printing distortion and black point missing caused by marking failure, by improving the accuracy of recognition to control error, recognition rate rapid declination due to printingdistortion, black point printing incompleteness can be avoided , can serve the needs of large and medium-sized examinations in schools well.

Description

technical field [0001] The invention relates to the technical field of marking algorithm image recognition, and more specifically, to an image mode-based answer sheet scoring and marking system. Background technique [0002] At present, there are many styles of the unified scoring system based on the template test paper, but the popular main idea is to set four black corner points on the four edges (such as figure 1 shown), and then normalized to the same space for comparison, and then count the features on the test paper, and finally obtain effective information and count the test paper scores, limited by the current shortage of handwriting recognition technology and language analysis technology, currently on the market The objective questions are graded automatically, and the subjective questions are graded through the Internet. Just as the Chinese patent application number 201510400317.9 discloses an image-based answer sheet scoring and marking system, it is based on the...

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): G06K9/00G06K9/20G06K9/32G06K7/14G06K9/62G06Q50/20
CPCG06K7/1417G06Q50/20G06V30/40G06V10/22G06V10/25G06F18/2148G06F18/24
Inventor 李可佳唐晓微郭晨阳
Owner JIANGSU QUSU EDUCATION TECH
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