Automatic Annotation Method of Terror Image Based on Integrated Deep Migration Learning
Wenjun Zhao · Academic Journal of Computing & Information Science · 2021
With the continuous development of Internet technology, anti-terrorism images have become an important part of network anti-terrorism. In this paper, a method of automatic annotation of terror images based on integrated deep migration learning is proposed by combining parameter migration and ensemble learning, which can help filter terror information in web pages. Firstly, the deep convolution neural network model is used to train the terror image model in the source domain, and then the migration from the source domain to the target domain is realized through the migration learning technology. Then, the integrated learning framework is used to integrate the transfer learning model. Experimental results show that the accuracy and recall rate of the proposed algorithm are obviously improved.