Supercharge Your Innovation With Domain-Expert AI Agents!

An FHOG feature-based automatic statistical method and device for scores of test paper

A statistical method, SP-FHOG technology, applied in the field of automatic statistics of network test paper scores based on FHOG features, can solve the problems of increasing workload and achieve the effects of enhanced feature description performance, strong rotation robustness, and improved accuracy

Active Publication Date: 2019-05-10
HENAN POLYTECHNIC UNIV
View PDF6 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Manually counting test paper scores will add additional workload

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 FHOG feature-based automatic statistical method and device for scores of test paper
  • An FHOG feature-based automatic statistical method and device for scores of test paper
  • An FHOG feature-based automatic statistical method and device for scores of test paper

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0065] Embodiment 1 of the present invention proposes a method for automatically counting scores of DBN (Deep BeliefNets) network test papers based on FHOG (Fused Histogram Oriented Gradient) features. The LeNet-5 model proposed in 2012 can recognize handwritten digits more accurately, but the model requires a fixed scale (28*28) to recognize handwritten digit images. The model is not robust to digit rotation. For handwritten digital samples with a large rotation angle, the recognition rate has a certain decrease. In the statistics of test paper scores, the scale of handwritten numbers is uncertain, and the rotation angle is uncertain. Therefore, the present invention uses scale-independent FHOG features that are more robust to digital rotation to replace the original grayscale image information. In this method, the foreground and background discrimination function is firstly applied in the original image of the test paper to determine the score area. Then, apply the neares...

Embodiment 2

[0100] Please refer to Figure 11 Shown, a kind of network test paper score automatic statistics device based on FHOG feature, is the virtual device of embodiment one, and it comprises:

[0101] The transformation module 10 is used to perform scale transformation on each single-digit handwritten sample in the Mnist sample database and each double-digit handwritten sample in the NIST SD19 sample database, to obtain a single-digit handwritten sample image corresponding to each single-digit handwritten sample A double-digit handwriting sample image corresponding to each double-digit handwriting sample;

[0102] The first acquisition module 20 is used to extract the SP-FHOG feature of the single-digit handwritten sample image and the double-digit handwritten sample image;

[0103] The training module 30 is used to input the SP-FHOG feature of the single-digit handwritten sample image and the SP-FHOG feature of the double-digit handwritten sample image into the neural network resp...

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 automatic test paper score statistical method based on FHOG characteristics. The automatic test paper score statistical method comprises the following steps: S1, carrying out scale transformation on a single-digital handwriting sample and a double-digital handwriting sample; S2, extracting SP-FHOG features of the single-number handwritten sample image and the double-number handwritten sample image; S3, training the neural network to obtain a single-digit identification model, a double-digit identification model and a digit number identification model; S4, extractingSP-FHOG features of each segmentation result image; S5, carrying out SP-FHOG features of the segmentation result image; and inputting the SP-FHOG features into a digital number recognition model and asingle digital recognition model or a digital number recognition model for recognition. The invention further provides an automatic test paper score statistics device based on the FHOG characteristics. The method is high in precision, and can effectively perform score statistics on the test paper.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a method and device for automatically counting scores of network test papers based on FHOG features. Background technique [0002] Professional accreditation is the basic way for developed countries to conduct professional evaluation of higher education. Professional accreditation for a program means that its graduates meet industry-recognized quality standards. It is reported that by the end of 2017, the Higher Education Teaching Evaluation Center of the Ministry of Education and the China Engineering Education Professional Certification Association have certified 846 engineering majors in 198 colleges and universities across the country. Passing professional certification marks that the quality of these majors has achieved international substantial equivalence, and has entered the "first phalanx" of global engineering education. The three major concepts of profession...

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): G06K9/46G06K9/62G06K9/00
Inventor 赵运基马义超刘晓光张新良范存良
Owner HENAN POLYTECHNIC UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com