Image filtering method and device

Abstract

The invention discloses an image filtering method and a device capable of greatly reducing misjudgment ratio in a filtering process and quickly and accurately filtering porn. The image filtering method, provided by the embodiment of the invention, comprises the steps of: extracting a skin region in an original picture by picture region segmentation, calculating area ratio of the skin region in the original picture, permitting the original picture when the area ratio is smaller than a first threshold, obtaining a clipped picture including the skin region according to the original picture when the area ratio is more than the first threshold and less than a second threshold, filtering the original picture by the area ratio of the skin region in the clipped picture, detecting a face skin region in the original picture when the area ratio is more than the second threshold, and filtering the original picture according to the area ratio of the face skin region in the skin region.

Description

technical field [0001] The present invention relates to the technical field of graphics and image processing, in particular to a picture filtering method and device. Background technique [0002] Since the advent of the Internet, pornographic pictures have also appeared on the Internet. With the development of the Internet, it has reached the level of flooding. Pornographic pictures are extremely poisonous to young people. How to accurately and effectively filter pornographic pictures has always been an arduous task. [0003] The early technology is to analyze the behavior of the characters in the picture to obtain the semantic information of the image by judging the relative position and movement of the characters in the picture, but this method has many defects, such as treating group photos or even humanoid sculptures as pornographic pictures. [0004] The current yellow image filtering mainly relies on skin color to detect pictures. Although this method has improved filt...

AI Technical Summary

Problems solved by technology

[0004] The current yellow image filtering mainly relies on skin color to detect pictures. Although this method has improved filtering accuracy compared with earlier methods, it is easy to misjudge only relying on skin color to filter, such as some areas with large skin color. Normal pictures, such as big headshot photos, face photos, etc., are easily misjudged as yellow pictures and filtered out, resulting in low accuracy of picture recognition and poor picture filtering effect

Images