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

A method for removing station captions and subtitles in an image based on a deep neural network

A deep neural network and image-in-image technology, applied in the field of removing logos and subtitles in images based on deep neural networks, can solve problems such as limitations of application scenarios, poor ability of complex scenes, and large amount of calculations to achieve visual effects The effect of realism, strong fitting ability, and good restoration results

Active Publication Date: 2019-03-15
CHENGDU SOBEY DIGITAL TECH CO LTD
View PDF7 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] The purpose of the present invention is: in order to solve the problems that the existing image restoration methods have poor ability to restore complex scenes in audio-visual images, require a large amount of calculation, and have limitations in application scenarios, the present invention provides a deep neural network-based The method of removing the logo and subtitles in the image, combining the characteristics of the convolutional neural network and the generation of the confrontation network, constructs the image repair model, and trains the image repair model with a large amount of data, and then removes the video frames that need to remove the logo and subtitles Bring in the image repair model for calculation, and automatically get the image frame without the logo and subtitles. The repair has strong real-time performance and a wide range of applications

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 for removing station captions and subtitles in an image based on a deep neural network
  • A method for removing station captions and subtitles in an image based on a deep neural network
  • A method for removing station captions and subtitles in an image based on a deep neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0050] Such as figure 1 As shown, this embodiment provides a method for removing the logo and subtitles in an image based on a deep neural network, including the following steps:

[0051] S1. Establish an image repair model: the image repair model is composed of a "U-net" network and a GAN, and the "U-net" network is used as a Generator of the GAN;

[0052] S2. Image preprocessing of the training set: crop or scale the images in the training set to a limited size to obtain the training image. In this embodiment, the length and width of the training image are limited to 512*512mm. According to the area where the station logo and subtitles are usually located, the The training images are logically partitioned as figure 2 Area 1, area 2 and area 3 are shown, wherein area 1 is the area where the station logo is located under normal conditions, area 2 is the area where subtitles are located under normal conditions, and corresponding Mask1 and Mask2 are generated in area 1 and are...

Embodiment 2

[0071] This embodiment is further optimized on the basis of the embodiment, specifically:

[0072] The class "U-net" network in S4 is composed of a convolutional layer and a deconvolution layer, and the processing flow of the class "U-net" network to the training image P1 and the training image P2 includes a downsampling process and an upsampling process, so In the down sampling process, the feature size is reduced by a convolution kernel with a step size of 2, and in the up-sampling process, the feature size is enlarged by a convolution kernel with a step size of 1 / 2; the class "U-net" network performs training image P1 When calculating with the training image P2, there is a ReLU activation function after each convolution and deconvolution operation.

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 removing station captions and subtitles in an image based on a deep neural network, and relates to the technical field of image restoration, and the method comprises the following steps: S1, building an image restoration model; S2, preprocessing images of the training set; S3, processing training data: taking the training image as a real image Pt; Setting a pixel point RGB value in a Mask1 region in the training image as 0, and taking the pixel point RGB value as a training image P1; Setting a pixel point RGB value in a Mask2 region in the training image as0, and taking the pixel point RGB value as a training image P2; S4, training the image restoration model to obtain a trained image restoration model; S5, image restoration; The method comprises the following steps of: preprocessing an image or a video needing to remove station captions and subtitles; According to the image restoration method, based on the deep learning idea, station captions andsubtitles in the image are automatically and rapidly removed, the processing process is clear and clear, restoration real-time performance is high, and the application range is wide.

Description

technical field [0001] The present invention relates to the technical field of image restoration, and more specifically relates to a method for removing a logo and subtitles in an image based on a deep neural network. Background technique [0002] With the rapid development of the Internet and mobile Internet, the total number of pictures and videos on the Internet and the playback time are constantly increasing. In 2017, the total daily video playback on YouTube alone exceeded 1 billion hours. There are station logos and subtitles in some video images, and the original video images cannot be obtained due to age or other reasons. How to remove the station logo and subtitles in real time and quickly in the existing video images to reduce the impact of the station logo or subtitles? Unfavorable interference of content, so that the audience can obtain a good visual experience is an urgent problem to be solved at present. [0003] Existing image restoration methods include the ...

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): G06K9/32G06K9/34G06N3/04G06N3/08
CPCG06N3/08G06V20/635G06V10/267G06N3/045
Inventor 王炜李杰温序铭谢超平
Owner CHENGDU SOBEY DIGITAL 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