Pornographic video detection method based on semi-supervised learning of images
A semi-supervised learning and video detection technology, applied in instruments, character and pattern recognition, computer parts, etc., can solve the problems of complex background, inaccurate detection results, and incomplete extraction of foreground areas.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0040] The implementation of the present invention will be described in detail below in conjunction with the examples.
[0041] A pornographic video detection method based on graph semi-supervised learning, the steps are as follows:
[0042] Step 1, foreground area extraction based on motion information, the steps are as follows:
[0043] a) Detect the shot boundary in the video based on the dual domain value algorithm.
[0044] Extract the histogram information of the three components of R, G, and B in the video frame, and calculate the difference value of the histogram of adjacent frames. Calculated as follows:
[0045] Z ( k , k + 1 ) = 1 M Σ i ∈ { R , G , B ...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


