Unlock instant, AI-driven research and patent intelligence for your innovation.

Method for automatically splitting test paper layout questions

A test paper and layout technology, applied in neural learning methods, instruments, biological neural network models, etc., can solve problems such as time-consuming, inflexible expansion of data, etc.

Inactive Publication Date: 2020-01-17
安徽七天网络科技有限公司
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Aiming at the deficiencies of the prior art, the present invention provides a method for automatically splitting test paper layout questions. By introducing deep learning technology into the automatic splitting of test paper layout questions, it solves the problem of splitting a single test paper layout question based on a fixed position. Inflexible expansion caused by test questions and time-consuming manual labeling of data

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
  • Method for automatically splitting test paper layout questions
  • Method for automatically splitting test paper layout questions
  • Method for automatically splitting test paper layout questions

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0030] Such as Figure 1-3 As shown, the present invention provides a technical solution: a method for automatically splitting test paper layout titles, including a data simulation part, a picture feature extraction part and a feature layer prediction part:

[0031] Data simulation part: Mainly describe the idea of ​​making training data used in this method. The basic idea is to use programming language to develop programs and automatically simulate various types of interview papers required. First, randomly select a background image and resize it to a size of 1024x768 , randomly select a type of layout (such as filling in the blanks, multiple choice questions, etc.), and generate a layout interview question of text + formula + chart structure according to the type, and control the line spacing between each question through the program. The layout of each simulation test paper The size of the font and font size between the questions is randomly selected to ensure that the simu...

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 the technical field of image target detection and recognition, and discloses a method for automatically splitting test paper layout questions. The system is designed based onan improved yolov3 network architecture and mainly comprises a simulation data generation part, a picture feature extraction part and a feature layer prediction part. The method proposes a method forautomatically splitting test paper layout questions. The method is mainly used for automatically splitting test paper layout questions including common test papers in mathematics, Chinese, English andthe like. The test paper layout question splitting refers to the process that each question is independently and completely detected from test paper image data obtained in a scanning or shooting modethrough the method (including but not limited to the method), and coordinate position information of the questions in test paper is obtained.

Description

technical field [0001] The invention relates to the technical field of image target detection and recognition, in particular to a method for automatically splitting test paper layout questions. Background technique [0002] As an important application field in image processing, object detection has been widely used in intelligent transportation, security, medical treatment, education and other fields. At the same time, with the continuous application of deep learning methods, the accuracy of target detection has been greatly improved, especially in scenes where the target object has specific physical characteristics, the target detection accuracy is very high. However, the application of deep learning technology in the test paper layout topic splitting is less. This method introduces the powerful convolutional neural network of deep learning technology into the test paper layout topic splitting, and proposes a new method that specifically solves the test paper layout topic s...

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): G06K9/00G06K9/62G06N3/08
CPCG06N3/08G06V30/40G06V2201/07G06F18/214
Inventor 严军峰董平陈家海叶家鸣吴波
Owner 安徽七天网络科技有限公司