Portrait head background blurring method based on top camera soft segmentation

A background blur, camera technology, applied in the field of computer vision, can solve the problem that the portrait background cannot be accurately blurred and so on

Active Publication Date: 2019-08-09
PLEX VR DIGITAL TECH CO LTD
View PDF3 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of the above-mentioned defects of the prior art, the technical problem to be solved by the present invention is to overcome the problem that the portrait background cannot be accurately blurred in the prior art

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
  • Portrait head background blurring method based on top camera soft segmentation
  • Portrait head background blurring method based on top camera soft segmentation
  • Portrait head background blurring method based on top camera soft segmentation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] The following describes several preferred embodiments of the present invention with reference to the accompanying drawings, so as to make the technical content clearer and easier to understand. The present invention can be embodied in many different forms of embodiments, and the protection scope of the present invention is not limited to the embodiments mentioned herein.

[0052] In the drawings, components with the same structure are denoted by the same numerals, and components with similar structures or functions are denoted by similar numerals. The size and thickness of each component shown in the drawings are shown arbitrarily, and the present invention does not limit the size and thickness of each component. In order to make the illustration clearer, the thickness of parts is appropriately exaggerated in some places in the drawings.

[0053] Such as figure 1 As shown, the portrait shooting solution of the present invention innovatively combines the tof camera to...

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 portrait head background blurring method based on top camera soft segmentation. The preparation method comprises the following steps: S1, analyzing portrait head noise, S2, extracting deep learning-based semantic information under a top camera, S3, carrying out top soft segmentation based on the top camera, and S4, carrying out convolution processing on the whole photo byutilizing Gaussian convolution of a soft segmentation weight and top parameters to realize the blurring of the portrait background. According to the invention, a portrait mode effect is greatly optimized by using an alpha-matting technology. By means of the technology, hairline information at the edge of a portrait can be completely reserved, and background information which does not belong to part of people is blurred. After the algorithm provided by the invention is integrated into the display card of the mobile phone, the shooting blurring speed is basically the same as the shooting speedof the iPhone.

Description

technical field [0001] The invention relates to the field of computer vision, in particular to a method for blurring the background of a portrait head based on soft segmentation of a tof camera. Background technique [0002] At present, many mobile phone and professional camera manufacturers have launched their own portrait shooting systems. For example, Xiaomi, Huawei, and Apple mobile phones have their own optimization algorithms for shooting people alone. But neither the front HD camera nor the rear dual or triple camera can optimize the edges of characters very well. The present invention compared and experimented with the results obtained by the major mobile phone camera manufacturers currently on the market for shooting the same characters, and found that more mobile phone algorithms use the simulated large aperture technology to achieve the background blur function or use face recognition technology to perform character beautification . But such a technique can eas...

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): G06T3/00G06N3/04G06N3/08G06T5/00G06T7/194G06T7/90
CPCG06T3/0012G06T7/194G06T5/002G06N3/08G06T7/90G06T2207/10024G06N3/044G06N3/045
Inventor 马原曦王岑张迎梁
Owner PLEX VR DIGITAL 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