A color gamut detection method for ultra-high-definition film sources for multi-category image conversion and comparison
An image conversion, multi-category technology, applied in neural learning methods, character and pattern recognition, instruments, etc., can solve problems such as damage to the enthusiasm of the ultra-high-definition market, and the quality of ultra-high-definition programs does not meet the requirements of technical standards, so as to reduce overfitting. The effect of reducing the risk of integration, the overall detection accuracy of the system, and reducing the difficulty of training
Active Publication Date: 2022-03-11
ACADEMY OF BROADCASTING SCI STATE ADMINISTATION OF PRESS PUBLICATION RADIO FILM & TELEVISION +1
View PDF8 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] However, in practical applications, the quality of ultra-high-definition programs may not meet the requirements of technical standards in various links such as program production, exchange, and transmission, which seriously damages the enthusiasm of the ultra-high-definition market
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0022] The implementation of the present invention will be described in further detail below in conjunction with the accompanying drawings.
[0023] A method for detecting the color gamut of an ultra-high-definition film source for multi-category image conversion and comparison, comprising the following steps:
[0024] Step 1. Construct a color gamut detection network for multi-category image conversion and comparison, which is used to detect the color gamut of the video source. The detection of video source color gamut includes two color gamut categories: BT.709 and BT.2020.
[0025] Such as figure 1 As shown, the color gamut detection network constructed in this step includes image conversion and contrast layer, residual unit Block1-5, fully connected layer and output layer. The size of the input image is uniformly 224×224×3. First, the input image is converted through the image conversion and contrast layer, and then the output of this layer is sent to Block1, Block2, Blo...
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
Login to View More Abstract
The invention relates to an ultra-high-definition film source color gamut detection method for multi-category image conversion and comparison. The color gamut of a video source is detected; the image conversion and comparison layer is constructed to convert the input image, and the reference and comparison between different categories of features are added; the residual network is used as the initial network to combine the original input image and the converted image At the same time, the initial network is input; the color gamut detection network is trained to obtain the color gamut classification models of BT.709 and BT.2020, and the color gamut category of the image is classified by the color gamut. The invention has a reasonable design, detects the technical conformity of the color gamut of the ultra-high-definition video source, attributes the color gamut detection problem to an image classification problem, and combines the convolutional neural network in the image classification task to obtain a good color gamut The detection results have greatly improved the overall detection accuracy of the system.
Description
technical field [0001] The invention belongs to the technical field of computer vision image classification, in particular to an ultra-high-definition film source color gamut detection method for multi-category image conversion and comparison. Background technique [0002] At present, the new generation of TV technology represented by ultra-high-definition TV has shown a trend of rapid development in recent years. Compared to HDTV, UHDTV is not just an increase in resolution, but also includes high frame rate, high bit depth, wide color gamut and high dynamic range. As a key technology of UHD TV, wide color gamut can present richer colors, giving viewers an immersive visual experience. [0003] However, in practical applications, the quality of ultra-high-definition programs may not meet the requirements of technical standards in various links such as program production, exchange, and transmission, which seriously damages the enthusiasm of the ultra-high-definition market. ...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06V10/764G06V10/82G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/241
Inventor 周芸胡潇郭晓强李小雨魏建超梁琳琳
Owner ACADEMY OF BROADCASTING SCI STATE ADMINISTATION OF PRESS PUBLICATION RADIO FILM & TELEVISION