Image zooming method based on significance model

An image scaling and image technology, applied in image data processing, graphic image conversion, instruments, etc., can solve the problems of image content distortion and inability to protect, achieve a smooth transition of significance, reduce the influence of artificial traces, and ensure integrity. Effect

Inactive Publication Date: 2017-07-21
TAIYUAN INST OF TECH
View PDF5 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method is relatively simple, but there are two problems. One is that all the scenes in the image are reduced or enlarged in the same proportion during the image scaling process, so that some important objects in the image cannot be protected to highlight the key points of the image; Changing the aspect ratio of the image will cause serious distortion of the image content

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
  • Image zooming method based on significance model
  • Image zooming method based on significance model
  • Image zooming method based on significance model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0014] Step 1 Preprocess the input image and convert the image from RGB color space to CIELAB color space:

[0015] Step 1.1 RGB to XYZ conversion

[0016] Suppose r, g, b are the three channels of the pixel, and the value range is [0,255]. The conversion formula is as follows:

[0017]

[0018]

[0019] The gamma function above is used to edit non-linear tone of the image, the purpose is to improve the contrast of the image;

[0020]

[0021] Step 1.2 XYZ Go to CIELAB

[0022] In the following two formulas, L*, a*, and b* are the values ​​of the three channels of the final LAB color space. X, Y, Z are the values ​​​​calculated after converting RGB to XYZ, and X n , Y n ,Z n The general default is 95.047, 100.0, 108.883;

[0023]

[0024]

[0025] Step 2 Calculate the salient region of the image by using the method based on the superpixel global contrast;

[0026] Step 2.1 Perform superpixel segmentation on the image based on the HSLIC (Hexagonal Simple L...

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 image zooming method based on a significance model. The method comprises steps of firstly, preprocessing an input colorful image; then, using a method based on superpixel global contrast to calculate to obtain a significance image of the image; combining a result of a significance detection and gradient information of the image to obtain an energy matrix; and by combining the energy matrix, using a line cutting algorithm to zoom the original image, thereby achieving adjustment of the image size. According to the invention, a significance region of the image can be detected and when the image size is freely changed, the main body features in the image are kept unchanged.

Description

technical field [0001] The invention relates to the technical field of image zooming and processing, in particular to an image zooming method based on a saliency model. Background technique [0002] Image scaling technology is a common technology in the field of image processing, which is used to change the spatial resolution of digital images. Traditional image scaling often uses interpolation methods to change the image resolution, such as bilinear interpolation, bicubic interpolation, and so on. This method is relatively simple, but there are two problems. One is that all the scenes in the image are reduced or enlarged in the same proportion during the image scaling process, so that some important objects in the image cannot be protected to highlight the key points of the image; Changing the aspect ratio of an image can severely distort the image content. The technical problem solved by this patent is the scaling technology to keep the image subject area from being defo...

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): G06T3/40
CPCG06T3/4023
Inventor 王俊秀刘晋钢
Owner TAIYUAN INST OF TECH
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