Intelligent method and system integrating deep learning and logical judgment

A technology of logical judgment and deep learning, applied in the field of image information recognition, which can solve the problems of easy missed recognition and low recognition accuracy.

Active Publication Date: 2021-08-20
江西风向标智能科技有限公司
View PDF11 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Based on this, the purpose of the present invention is to provide an intelligent method and system that integrates deep learning and logical judgment to solve the technical problems of low recognition accuracy and easy to miss recognition in the existing recognition option area

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 method and system integrating deep learning and logical judgment
  • Intelligent method and system integrating deep learning and logical judgment
  • Intelligent method and system integrating deep learning and logical judgment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0051] see figure 1, which shows the intelligent method of integrating deep learning and logical judgment in the first embodiment of the present invention, the method specifically includes step S01-step S05.

[0052] Step S01, acquiring an answer sheet image.

[0053] Among them, the image of the answer sheet can be captured by a camera or a scanner. When capturing the image of the answer sheet, try to ensure that the answer sheet is placed flat and has no obvious substances on the surface, so as to reduce the noise interference of subsequent images as much as possible.

[0054] Step S02, using a pre-trained image segmentation model to perform image segmentation on the answer sheet image, so as to identify each option area and its parameter information in each objective question area on the answer sheet image, and the parameter information includes coordinates information and size information.

[0055] In some cases of this embodiment, the image segmentation model is trained...

Embodiment 2

[0071] see image 3 , shows the intelligent method of integrating deep learning and logical judgment in the second embodiment of the present invention, and the method specifically includes steps S11 to S18.

[0072] Step S11, obtaining the answer sheet image, and obtaining the framed area in the answer sheet image to determine the objective question area, and then preprocessing the objective question area.

[0073] Wherein, the preprocessing is one or more of denoising processing, data enhancement processing, and resolution adjustment processing.

[0074] During specific implementation, the frame selection area in the answer sheet image can be manually selected by the operator, or can be automatically selected based on a reference point given by the operator.

[0075] Step S12, using a pre-trained image segmentation model to perform image segmentation on the answer sheet image, so as to identify each option area and its parameter information in each objective question area on...

Embodiment 3

[0094] Another aspect of the present invention also provides an intelligent system that integrates deep learning and logical judgment, please refer to Figure 4 , which shows the intelligent system that integrates deep learning and logical judgment in the third embodiment of the present invention, and the intelligent system that integrates deep learning and logical judgment includes:

[0095] Image acquisition module 11, used to acquire the answer sheet image;

[0096] The image segmentation module 12 is used to perform image segmentation on the answer sheet image using a pre-trained image segmentation model, so as to identify each option area and its parameter information in each objective question area on the answer sheet image. Parameter information includes coordinate information and size information;

[0097] A missing judgment module 13, configured to judge whether there is a missing option area according to the coordinate information of the option area;

[0098] The 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 provides an intelligent method and system integrating deep learning and logical judgment. The method comprises the following steps: acquiring an answer sheet image; performing image segmentation on the answer sheet image by using a pre-trained image segmentation model so as to identify each option area and parameter information thereof on the answer sheet image, the parameter information including coordinate information and size information; according to the coordinate information of the option area, judging whether a missing option area exists or not; if yes, supplementing the missing option area according to the coordinate information of the adjacent option area of the missing option area and the size information of the option area; and outputting each option area of the identified answer sheet image. By fusing the deep learning neural network model and the logic judgment, the method successfully solves the problems that the fuzzy image feature points are few, the image noise is large and the image noise is difficult to process, improves the identification precision of the option region, and can well solve the problem of missed identification.

Description

technical field [0001] The invention relates to the technical field of image information recognition, in particular to an intelligent method and system that integrates deep learning and logical judgment. Background technique [0002] In order to speed up the efficiency of reviewing test papers, answer sheets are generally used to fill in the answers. Since objective questions such as multiple-choice questions and admission ticket numbers on the answer sheet can be image-matched with the correct answer sheet module to automatically identify right and wrong, the objective question can be quickly completed. topic review work. Among them, the premise of quick review of objective questions on the answer sheet is to be able to automatically identify each option area (such as [A], etc.) in the image of the answer sheet. [0003] In the prior art, the current method of identifying the option area is as follows: First, obtain the template answer sheet, and the user selects the objec...

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): G06K9/32G06K9/34G06K9/40G06K9/62G06N3/04G06N3/08
CPCG06N3/04G06N3/08G06V20/63G06V10/30G06V10/267G06F18/22G06F18/214
Inventor 刘凡
Owner 江西风向标智能科技有限公司
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap