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

Automatic filter implementation method, storage medium, device and system

An implementation method and filter technology, applied in image data processing, instruments, biological neural network models, etc., can solve problems such as time-consuming and time-consuming, and achieve the effect of reducing preparatory work and ensuring live broadcast experience.

Active Publication Date: 2019-02-12
WUHAN DOUYU NETWORK TECH CO LTD
View PDF9 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In the live broadcast industry, in order to present the audience with a better sense of picture and bring a good viewing experience to the audience during the live broadcast, the anchor usually uses filter effects to match the current live broadcast scene, but every time the anchor broadcasts The scene will change during the live broadcast, and there are many types of filter effects. Every time the host is live broadcasting, he needs to manually select and set the filter effects. many

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
  • Automatic filter implementation method, storage medium, device and system
  • Automatic filter implementation method, storage medium, device and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0042] see figure 1 As shown, the embodiment of the present invention provides an automatic filter implementation method, which is used to realize the automatic replacement of filter special effects by the anchor during the live broadcast, without the anchor needing to manually adjust and replace. The automatic filter implementation method of the embodiment of the present invention specifically includes the following steps:

[0043]S1: Obtain multiple images as training samples to train the neural network model, and each image contains a marker used to mark the scene. This step is mainly to enable the neural network model to have the ability to recognize specific markers. The markers include solid-color walls, billboards and sky. For example, you can use images containing solid-color walls as training samples to train the neural network model, or use images containing sky as training samples to train the neural network model, or use images containing The images of billboards ...

Embodiment 2

[0062] An embodiment of the present invention provides a storage medium on which a computer program is stored, wherein the computer program is executed by a processor to implement the following steps:

[0063] Obtain multiple images as training samples to train the neural network model, and each image contains a marker for marking the scene;

[0064] Capture the live broadcast screen as the image to be detected, and use the trained neural network model to detect the content contained in the image to be detected;

[0065] When it is detected that the image to be detected contains a marker, call out the filter effect of the scene corresponding to the marker as the filter effect of the current live broadcast;

[0066] Among them, the landmarks include solid-color walls, billboards and sky: when the landmarks in the image to be detected are detected to be solid-color walls, the white filter is used as the filter effect of the current live broadcast; when the landmarks in the image...

Embodiment 3

[0072] see figure 2 As shown, the embodiment of the present invention provides an electronic device, and the electronic device includes a training unit, a detection unit, and a filter and special effect execution unit.

[0073] The training unit is used to obtain multiple images as training samples to train the neural network model, and each image contains a marker used to mark the scene; the detection unit is used to intercept the live screen as the image to be detected, and use the training to complete The final neural network model detects the content contained in the image to be detected; the filter effect execution unit is used to call out the filter effect of the scene corresponding to the marker when it detects that the image to be detected contains a marker as the current live filter mirror effects;

[0074] Among them, the landmarks include solid-color walls, billboards, and the sky: when the detection unit detects that the landmarks in the image to be detected are ...

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 an automatic filter realizing method, a storage medium, a device and a system, which relate to the field of photographing beauty. The method comprises the following steps of acquiring a plurality of images as training samples, and training a neural network model, wherein each image contains a marker for marking a scene; intercepting the live broadcast picture as the image to be detected, and using the trained neural network model to detect the content of the image to be detected; when the marker is detected in the image to be detected, calling the filter special effectcorresponding to the scene of the marker as the filter special effect of the current live broadcast, wherein a mark comprises a solid color wall, a billboard and a sky: when that mark in the image tobe detected is detected as a solid color wall, using a white filter as a filter special effect of the current live broadcast. By judging the live broadcast scene of the current anchor, the invention automatically calls out the filter special effect corresponding to the scene as the filter special effect of the current live broadcast.

Description

technical field [0001] The present invention relates to the field of photo-beautification, in particular to an automatic filter realization method, storage medium, equipment and system. Background technique [0002] At present, when people take selfies or videos with cameras, it has become the norm to adjust the real-time beauty of the characters in the picture during the shooting process. Acne marks, changing the color tone of the entire picture or a certain part of the picture through filter effects adjustment, etc. Beauty has become the standard for beauty lovers. The filter effects include fairness, film, ocean, tenderness, girl, nature, memory, neon etc. [0003] In the live broadcast industry, in order to present the audience with a better sense of picture and bring a good viewing experience to the audience during the live broadcast, the anchor usually uses filter effects to match the current live broadcast scene, but every time the anchor broadcasts The scene will c...

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): G06T5/00G06N3/02
CPCG06N3/02G06T2207/20081G06T5/92
Inventor 李亮
Owner WUHAN DOUYU NETWORK 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