A new model for small target adult image recognition

Abstract

Abstract With the advent of the era of 5G high speed and massive information, the audience of netizens is developing at a younger age, and the proliferation of adult images on the Internet is becoming more and more serious. The recognition and filtering of adult pictures has become very important to prevent young people from contacting harmful information. But, because of the wide variety of adult images, automatic recognition in these pictures is a very difficult task. This paper proposes a new model based on Residual neutral network. Our method consists of two parts. The first part is to divide images into large target skin color image and target skin color image according to the proportion of skin color pixels of the image; The second part is to input the two types of images into two different models for recognition. According to the results of comparative experiments, the proposed network can further improve the classification accuracy of adult images of small targets with excessive background noise, which is better than other single model.