Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Data visualization color matching extraction method based on image clustering

An extraction method and image clustering technology, applied in image data processing, image analysis, filling planes with attributes, etc., can solve the problems of no aesthetic communication, blunt simplicity, etc.

Pending Publication Date: 2020-10-13
COMMUNICATION UNIVERSITY OF CHINA
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] In addition, programmers generally use random number color matching for changes. The characteristic of this color matching is that the colors generally do not repeat, but the color matching is completely random, blunt and simple, and does not have aesthetic communication

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
  • Data visualization color matching extraction method based on image clustering
  • Data visualization color matching extraction method based on image clustering
  • Data visualization color matching extraction method based on image clustering

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0090] Example, in the above S3:

[0091] Taking the beginning of the first episode of "Story of Yanxi Palace" as an example, the data set to be clustered is the shot frame set separated by the shot segmentation algorithm in the previous step. The average length of each shot is about 4 seconds, with a total of 120 frames. For each shot Perform key frame extraction, and dynamically set the number of extracted key frames according to the length of each shot. The length of the video is 1 minute and 49 seconds, with a total of 28 shots and 68 key frames extracted.

[0092] Embodiment, in above-mentioned S5:

[0093] Taking the first episode of "Story of Yanxi Palace" as an example, the frame rate is 30, the duration is 45 minutes, a total of 81,790 frames of video, 648 shots are segmented, 1,714 key frames are extracted, and 1,714 key frames are generated. The 1714 sets of timing color schemes corresponding to key frames provide color rendering that changes with video timing 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 data visualization color matching extraction method based on image clustering. The method comprises the steps: inputting a video or a picture; segmenting the video through asize-adjustable sliding window to obtain a plurality of shot video frames; extracting one or more key frames of each shot video frame after segmentation through a color histogram frame difference method and a clustering algorithm; clustering the HSV color values of the pixels in the extracted key frame pictures one by one to obtain a color matching scheme of each key frame picture; or clustering the HSV color values of the pixels in the input picture to obtain a color matching scheme of the picture; and outputting a color matching scheme, and applying the current color matching scheme to datavisual color matching. The method is low in time complexity and can be used for picture extraction color matching or video extraction color matching, a color matching method changing along with a video playing time sequence is actually provided based on video color matching, an original picture is reversely filled with a color matching scheme, and the subjective approximate consistency of color extraction and the original picture is verified.

Description

technical field [0001] The present invention relates to the technical field of image processing of video content, relates to a method for extracting data visualization color matching based on image clustering, and in particular to a method for extracting video colors based on image clustering for data visualization color matching. Background technique [0002] When designing data charts, color is the most important element that makes up the appearance of the entire chart. Choosing correct and reasonable colors can make the chart more professional and beautiful; at the same time, in all visual channels involved in data visualization, color is the first visual element. A perceptual factor, data is most effectively encoded and communicated visually. [0003] The color matching of data visualization has always been a challenge for programmers, because the vast majority of data visualization programmers have a background in science and engineering, and lack the basic literacy of ...

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
IPC IPC(8): G06T11/40G06T7/90G06K9/00G06K9/46G06K9/62
CPCG06T11/40G06T7/90G06V20/49G06V10/56G06F18/23213
Inventor 李春芳石民勇李纪周王楷翔王丹煜
Owner COMMUNICATION UNIVERSITY OF CHINA
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
Eureka Blog
Learn More
PatSnap group products