Logo extraction device, and brightness adjusting method and device for logo
AssigneeTcl China Star Optoelectronics Technology Co., Ltd.
InventorsYang RAO, Leli PENG
Life of this patent
Estimating the term…
Abstract
The present application discloses a logo extraction device, and a brightness adjusting method and device for a logo. The logo extraction device includes an acquiring module, a gray-scale converting module, a weight processing module, and an extraction module. In the present application, by increasing a number of key frames in a process of logo extraction and using video frame weighting, the logo is extracted and thereby accuracy of logo extraction is improved.
Claims10
A logo extraction device, comprising:
- an acquiring module configured to acquire a continuous video image of preset frames during video playback and to acquire RGB values of pixels in each frame of the video image;
- a gray-scale converting module configured to convert the RGB values into a V-channel model and to obtain corresponding gray-scale values, thereby determining a gray-scale image corresponding to each frame of the video image according to the gray-scale values of the pixels;
- a weight processing module configured to perform weight calculation on the gray-scale values of the pixels in the gray-scale image of each frame of the video image and a gray-scale image of a previous frame of the video image, thereby performing weighting process to the gray-scale values of the pixels in each gray-scale image based on a weight value;
- and
- an extraction module configured to determine feature point information whose gray-scale value is less than a threshold value from the gray-scale image of the video image in the preset frames according to a preset algorithm, thereby using the feature point information to extract a logo from the video.
A brightness adjusting device for a logo, comprising:
- a logo extraction unit configured to acquire a continuous video image of preset frames during video playback and to extract the logo from the video image of the preset frames;
- a calculating unit configured to calculate a mean value of gray-scales of pixels in an area where the logo is located and a mean value of gray-scales of pixels of the video image, respectively;
- and
- a brightness adjusting unit configured to adjust a brightness of the logo by using a first algorithm based on the mean value of the gray-scales of the pixels in the area where the logo is located and the mean value of the gray-scales of the pixels of the video image.
A brightness adjusting method for a logo, comprising following steps:
- acquiring a continuous video image of preset frames and RGB values of pixels in each frame of the video image by an acquiring module during video playback;
- converting the RGB values into a V-channel model by a gray-scale converting module, obtaining corresponding gray-scale values, thereby determining a gray-scale image corresponding to each frame of the video image according to the gray-scale values of the pixels;
- performing weight calculation on the gray-scale values of the pixels in the gray-scale image of each frame of the video image and the gray-scale image of the previous frame of the video image, thereby performing weighting process to the gray-scale values of the pixels in each gray-scale image based on a weight value;
- determining feature point information whose gray-scale value is less than a threshold value from the gray-scale image of the video image in the preset frames according to a preset algorithm by an extraction module, thereby using the feature point information to extract the logo from the video;
- calculating a mean value of gray-scales of pixels in an area where the logo is located and a mean value of gray-scales of pixels of the video image by a calculating unit, respectively;
- and
- adjusting a brightness of the logo by using a first algorithm by a brightness adjusting unit based on the mean value of the gray-scales of the pixels in the area where the logo is located and the mean value of the gray-scales of the pixels of the video image.
Dependencies are inferred from the claim text.