Block chain copyright confirmation method based on video gene
A blockchain and video technology, applied in digital data authentication, program/content distribution protection, etc., can solve problems such as low video content comparison efficiency, achieve good promotion and application value, fast video rights confirmation, and small footprint Effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0052] Step b) includes the following steps:
[0053] b-1) Perform frame down processing on the original video. One is to unify the video gene frame rate of the video library, and the other is to reduce the computational overhead of video gene encoding.
[0054] b-2) Extract the binarized feature value for each frame of the original video after frame reduction processing. First image binarization feature value results cannot obtain the low frequency of the real image, but as long as the overall structure of the picture remains unchanged, the result value of its binarization feature remains unchanged. This process can avoid image scale, resolution, The impact of content adjustments such as watermarks, corner marks, subtitles, gamma correction, and color histograms.
[0055] b-3) Calculate the Hamming Distance (HammingDistance) between the image features of each frame of the encoded video work, truncate the feature where the Hamming distance is greater than 10% of the total le...
Embodiment 2
[0058] as attached figure 2 As shown, step b-2) comprises the following steps:
[0059] b-2.1) Remove the black borders around each frame of the original video after frame reduction. Discard the differences brought about by videos of different scales.
[0060] b-2.2) Reduce the image to a size of 8×8 pixels, and discard the differences caused by different sizes.
[0061] b-2.3) Convert the reduced image to grayscale.
[0062] b-2.4) The grayscale image is subjected to discrete cosine transform (DCT) of 16×16 resolution. After DCT transformation, the low-frequency part of the image is concentrated in the upper left corner, and this part of the information contains the low-frequency content of the image; the other parts are the high-frequency content of the image details.
[0063] b-2.5) Retain the content of the 8×8 matrix in the upper left corner of the image after discrete cosine transformation, and discard other high-frequency content.
[0064] b-2.6) Calculate the gra...
Embodiment 3
[0067] In step b-3), the shot descriptor includes the position in the video where the video shot is located, the number of frames contained in the video shot, the feature value of the first frame image of the video shot, and the Hamming distance between the feature values of each frame image .
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


