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

A method to automatically obtain the target image

A target image, automatic acquisition technology, applied in the field of image processing, can solve the problem that the target image is easily distorted and cannot be recognized by the machine.

Active Publication Date: 2019-02-01
HANGZHOU ZHUOJIAN INFORMATION TECH CO LTD
View PDF22 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to solve the problem that the target image collected in the prior art is easily distorted and cannot be recognized by the machine

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
  • A method to automatically obtain the target image
  • A method to automatically obtain the target image
  • A method to automatically obtain the target image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0047] Such as figure 1 As shown, this embodiment provides a method for automatically acquiring a target image. Among them, such as figure 2 As shown, the preferred size of the acquisition target in this embodiment is the first target 3 of A4 paper size and the content is a document, and the device is preferably a mobile phone 1, then the method for automatically acquiring the target image includes:

[0048] S101. Collect the first image of the target;

[0049] Wherein, the first image is preferably a low-resolution image with pixels of about 640×480. Such as figure 2 shown. Preferably, the mobile phone 1 enters a preview mode, and the first target 3 photographed is displayed in the window 2 of the mobile phone 1 . The first object 3 is displayed in the window 2 as a quadrilateral with a larger size and a smaller size. In addition to the first object 3, there are other interference objects (first interference object 4, second interference object 5) in the window.

[0...

Embodiment 2

[0093] Of course, it can be understood that the present invention is not limited thereto, and the present invention can also correct other regular-shaped objects.

[0094] Such as Figure 7 As shown, the mobile phone 1 shoots the second target 8 of a regular hexagon, and the second target 8 is displayed in the window 2 as a similar regular hexagon with a large near side and a small far side. Edge enhancement is performed on the first image of the second target 8; a regular hexagon is detected in the edge enhanced image; Taking the nearest side of the shape as a benchmark, according to the actual ratio of the second target 8, the candidate area 9 of the regular hexagon is set as an ideal area; the second image of the second target 8 is collected, so that the second target in the second image The shape of 8 adapts to the shape of the candidate area 9, that is, the distortion correction of the image of the second target 8 is completed, and a high-quality image that can be recogn...

Embodiment 3

[0097] Such as Figure 8 As shown, the mobile phone 1 shoots a circular third target 10 , and the third target 10 is displayed in the window 2 as an ellipse. Carry out edge enhancement to the low-resolution image of the third target 10; in the edge enhancement image, detect the circle in the image by Hough transform; and filter the shape that the ratio conforms to; set the candidate area 11 according to the radius that conforms to the shape; collect For the second image, the shape of the third target 10 in the second image is adapted to the shape of the candidate area 11, that is, the distortion correction of the third target image 10 is completed, and a high-quality image that can be recognized by a machine is obtained.

[0098] Of course, it can be understood that when the target is an ellipse, the candidate area is set based on the long radius and short radius conforming to the shape and the actual ratio of the target.

[0099] Other features in this embodiment are the sam...

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 a method for automatically obtaining a target image. The method comprises the steps of acquiring a first image of a target and conducting the edge enhancement treatment on the acquired image; detecting the image after the edge enhancement treatment to acquire a shape adapted to the target; adopting the shape as a candidate area of the target; acquiring the second image of the target and adjusting the acquired second image to adapt the target in the second image to the shape of the candidate area. Based on the method, the distorted images of targets can be corrected, so that the targets can be recognized by a machine.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a method for automatically acquiring a target image. Background technique [0002] With the development of image processing technology, almost all mobile smart terminals carry a camera function. Because the camera function is very convenient and fast, and can comprehensively record image content, people often use mobile smart terminals to shoot some objects, such as documents, reports, brochures and so on. In some cases, these photographed data contain some data that needs to be further processed by the terminal or computer, so some software in the terminal or computer will perform target extraction and recognition on the photographed data pictures. [0003] However, geometric deformation or distortion often occurs when photographing these targets with a terminal. Although the distorted content can be recognized by the human eye, the machine cannot recognize the distor...

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 Patents(China)
IPC IPC(8): G06T5/40
Inventor 刘立刘艳洋吴诗展
Owner HANGZHOU ZHUOJIAN INFORMATION TECH CO LTD
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