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

A method of background blurring based on salient region detection model

A technology of region detection and background blur, applied in biological neural network model, image analysis, image enhancement and other directions, can solve problems such as unclear boundaries, and achieve the effect of clear salient boundaries

Inactive Publication Date: 2021-04-27
FUZHOU UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Aiming at the problems of unclear boundaries in the existing background blurring methods, the present invention proposes a background blurring method based on a salient area detection model, which can detect the entire salient area, and can detect objects including multiple salient objects and small-scale salient objects. It performs well in various complex situations such as sexual objects, not only can accurately detect the complete salient area, but also the salient boundary is relatively clear

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 of background blurring based on salient region detection model
  • A method of background blurring based on salient region detection model
  • A method of background blurring based on salient region detection model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0061] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0062] Such as figure 1 As shown, the present invention provides a method for background blurring based on a salient region detection model, comprising the following steps:

[0063] Step S1: Obtain the original image;

[0064] Step S2: Construct a salient region detection model based on a convolutional neural network, and obtain a saliency map of the original image;

[0065] Step S3: put the saliency map into the fully connected conditional random field for training, and obtain the optimized saliency map;

[0066] Step S4: Binarize or segment the optimized saliency map to obtain the 01 matrix SBM, obtain the foreground index matrix IF and the background index matrix IB, which are defined as follows:

[0067] IF=SBM, IB=M×N-SBM

[0068] Among them, M×N is a matrix of all 1s with the same resolution as the original image;

[0069] Step S5: using the ...

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 background blurring based on a salient area detection model, comprising the following steps: acquiring an original image, constructing a salient area detection model convolution network to obtain a saliency map of the original image, and putting the obtained salient image into The fully connected conditional random field is trained to obtain the optimized saliency image, and then the optimized saliency map is binarized or segmented to obtain the 01 matrix, and the foreground index matrix and the background index matrix are obtained; the distance weighted average algorithm is used to realize the original Global blurring of the image; finally, the original foreground image and the blurred background image are stitched together to generate a blurred background image. The invention not only can accurately detect the complete salient area, but also has relatively clear salient boundaries, so that the features of the foreground image can be preserved when the background is blurred, and the image content of the foreground image is not damaged.

Description

technical field [0001] The invention relates to the technical field of digital image processing, in particular to a background blurring method based on a salient region detection model. Background technique [0002] Image background blurring is a very common processing process in image rendering, beautification, enhancement and other tasks. It can effectively highlight the target object and dilute the background information, thereby improving the visual effect. At present, some image processing software can complete this processing well, but its processing methods all need to manually mark the foreground area, which requires a lot of manpower and is not convenient for mass processing; It is a regular shape, and it is difficult to adapt to complex and changeable image content. The existing automatic background blur technology is immature in the extraction of foreground edges, resulting in unclear boundaries, cutting to the wrong area, etc. Contents of the invention [000...

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): G06T3/00G06T7/11G06N3/04
CPCG06T3/0012G06T7/11G06T2207/10004G06N3/045
Inventor 余春艳徐小丹陈立杨素琼王秀
Owner FUZHOU UNIV