Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Electronic paper marking identification method

An identification method and electronic scoring technology, applied in the field of information processing, can solve problems such as affecting identification and detection results, no smearing, failure of automatic scoring, etc.

Pending Publication Date: 2020-10-27
北京十六进制科技有限公司
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The identification and detection methods in the existing automatic marking system have high requirements for the background and clarity of the answer sheets or test papers. Affect the identification and detection results, resulting in the failure of automatic marking

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
  • Electronic paper marking identification method
  • Electronic paper marking identification method
  • Electronic paper marking identification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0014] The present invention will be described in further detail below.

[0015] A method for electronic marking and identification, comprising the following steps:

[0016] Step 1, constructing an image data set for target detection, the construction of an image data set for target detection includes image acquisition of the test paper image data obtained by the image segmentation function in the marking system, cleaning the image data after image acquisition, and discarding unqualified Sample, mark the position information of the correction symbol and the classification information on the cleaned image data,

[0017] Step 2: Carry out training and testing of the deep convolutional neural network on the image data set of the target detection, the training and testing of the deep convolutional neural network include preprocessing the image, and performing depth convolution on the preprocessed image The design, training and testing of the product neural network to obtain the o...

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 an electronic paper marking identification method. The method comprises the following steps: constructing an image data set for target detection, which mainly comprises the steps of real image acquisition, cleaning and labeling; training and testing a deep convolutional neural network, which mainly comprises the steps of image preprocessing, network structure design, training, testing, actual measurement and determination of a network model with the optimal effect; in the third part, the use of an optimal model mainly comprises the steps of giving coordinates and classification information of an output image, removing interference factors, and improving the paper marking recognition accuracy, so that no special printing requirement is required for test paper, teachers can use any dark color pen for correction in the test paper and can recognize the test paper, the requirement for the test paper background is lowered, the requirement for the sharpness of collected images is lowered, and the requirement for shooting equipment is lowered.

Description

technical field [0001] The invention relates to the technical field of information processing, in particular to an electronic examination and identification method. Background technique [0002] Online marking is based on computer network technology and electronic scanning technology, with the ultimate goal of controlling subjective test marking errors and realizing the principle of test fairness. The objective questions are controlled by computer programs to automatically score the information points filled by candidates. After the test paper is corrected by the marking teacher, the scanning is sent to the computer program, and the computer program recognizes and scores the examinee's answer sheet with the correction mark after the teacher's correction, and finally the computer program automatically counts and synthesizes the examinee's score. Marking method. The identification and detection methods in the existing automatic marking system have high requirements for the ba...

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
IPC IPC(8): G06K9/00G06K9/34G06K9/62G06Q10/06G06Q50/20G06N3/04
CPCG06Q10/0639G06Q50/205G06V30/413G06V10/267G06N3/045G06F18/214
Inventor 高峰
Owner 北京十六进制科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com