Method, system and device for automatically identifying and segmenting text image

A text image and automatic recognition technology, applied in the field of image recognition, can solve problems that affect the accuracy of search steps, poor user experience, and difficulty in unified processing, so as to reduce the loss of test question information, high recognition accuracy, and good user experience.

Active Publication Date: 2016-06-15
ALLWINNER TECH CO LTD
View PDF4 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Poor user experience due to factors such as screen size and narrow title text spacing
In addition, the completeness of the box questions directly affects the accuracy of the subsequent recognition and search steps, while there are too many differences in the manual selection method, it is difficult to deal with it uniformly, and corresponding preprocessing steps need to be designed
[0006] In the existing mainstream technology, the image area is roughly and automatically divided by the grid method. This method actually transfers the manual adjustment process after taking pictures to before tak

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, system and device for automatically identifying and segmenting text image
  • Method, system and device for automatically identifying and segmenting text image
  • Method, system and device for automatically identifying and segmenting text image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] Embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0052] figure 1 It is a method for automatically identifying and segmenting text images according to the present invention. In this embodiment, the method for automatically identifying and segmenting text images provided includes steps:

[0053] S1. Obtain the input text image through the camera on the mobile terminal, and perform preprocessing;

[0054] Specifically, when the user obtains the input text image through the camera on the mobile terminal, the user roughly aligns the crosshair on the screen with the area to be extracted, and then manually presses the camera key. Then the system automatically preprocesses the acquired text image, and the preprocessing steps include white balance, brightness compensation and grayscale processing.

[0055] According to a preferred embodiment of the present invention, the white balance processing can use a histog

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 a method for automatically identifying and segmenting a text image. The method comprises following steps: S1 obtaining an input text image and performing pretreatment; S2. segmenting the text image to determine a first target area; S3. operating a mark detector in the first target area, if the detection of the mark detector is successful, outputting a detection result to a judging device to perform confirmation and executing S4, if the detection of the mark detector is unsuccessful, executing S5; S4. fitting a second target area and cutting out the area on the basis of the mark position finally judged by the judging device and the information of the first target area; S5. fitting a third target area and cutting out by use of an image processing technology. The invention also discloses a system and device for automatically identifying and segmenting text image. Users only adjust a screen center reticle aiming at a test question expected to be searched in the text image and press a shooting button, and then a program can automatically segment the appointed test question area and perform uploading to realize complete and fluent user experience.

Description

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

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
Owner ALLWINNER TECH CO LTD
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