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

Implementation method and implementation device of automatic image area division

A technology of area division and automatic image, applied in image analysis, image data processing, instrument and other directions, can solve the problems of complex, inaccurate, time-consuming calculation, and achieve the effect of simple calculation

Active Publication Date: 2017-10-31
TENCENT TECH (SHENZHEN) CO LTD
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Existing technologies, such as the method of manually marking the area, are obviously time-consuming and inaccurate, while classic algorithms such as Graph cut require the user to select the object and background when processing each picture, which takes a long time and the calculation is relatively complex. Complicated, it will take more time on platforms with poor computing performance such as mobile phones

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
  • Implementation method and implementation device of automatic image area division
  • Implementation method and implementation device of automatic image area division
  • Implementation method and implementation device of automatic image area division

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0027] figure 1 It is a schematic flowchart of the implementation method of automatic image region division disclosed in the present invention. like figure 1 As shown, the realization method of the automatic image area division of the present invention comprises:

[0028] S11: Obtain the smooth structure tensor field corresponding to each pixel in the image.

[0029] The image in this step refers to the original image without any processing, please refer to figure 2 , figure 2 Shown is an image to be partitioned.

[0030] Please refer to image 3 , in step S11, the specific method for obtaining the smooth structure tensor field corresponding to each pixel in the image may include the following steps:

[0031] S111: Perform filtering processing on the image to obtain the gradient of each pixel.

[0032] For example, the sobel operator can be used to calculate the gradient of each pixel in the image in the x and y directions, and the specific formula is as follows:

...

no. 2 example

[0067] Figure 9 It is a schematic structural diagram of a device for realizing automatic image region division disclosed in the present invention. Such as Figure 9 As shown, the device 20 for implementing automatic image region division of the present invention includes: a smooth structure tensor field acquisition module 21 , an image detail degree acquisition module 22 , and an image region division module 23 .

[0068] The smooth structure tensor field acquisition module 21 is used to acquire the smooth structure tensor field corresponding to each pixel in the image; the image detail degree acquisition module 22 acquires the details of the image according to the cumulative change degree of the smooth structure tensor field degree; the image region division module 23 performs region division on the image according to the degree of detail of the image.

[0069] Please refer to Figure 10 , the smooth structure tensor field acquisition module 21 may further include: a g...

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 present invention relates to a method for realizing automatic image region division, which includes: obtaining the smooth structure tensor field corresponding to each pixel in the image; obtaining the details of the image according to the cumulative change degree of the smooth structure tensor field degree; divide the image into regions according to the degree of detail of the image. The present invention also provides a device for realizing automatic image region division that can realize the above method. The method and device for realizing automatic image area division provided by the present invention can complete image area division without any user interaction, the calculation is relatively simple, and image area division can also be realized on a platform with poor performance.

Description

technical field [0001] The invention relates to digital image processing technology, in particular to a method and device for realizing automatic image region division based on image detail. Background technique [0002] In the research and application of images, people are often only interested in some parts of an image, and these interested parts generally correspond to specific areas with special properties in the image (can correspond to a single area, or to multiple areas). area), called the target or foreground; while the other part is called the background of the image. In order to identify and analyze the target, it is necessary to isolate the target from an image, which is the problem to be studied in image segmentation. The so-called image segmentation, in a broad sense, is to group and cluster image pixels according to the similarity criteria of certain features or feature sets (including grayscale, color, texture, etc.) some consistent non-overlapping regions. ...

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): G06T7/11
Inventor 陈皓郭凯
Owner TENCENT TECH (SHENZHEN) 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