It has become a trend in recent years to use deep neural networks for colorization. However, previous methods often encounter problems with edge color leakage and difficulties in obtaining a plausible color output from the Euclidean distance. To solve these problems, we propose a new adversarial edgeaware image colorization method with multitask output combined with semantic segmentation. The system uses a generator with a deep semantic fusion structure to infer semantic clues in a given grayscale image under chroma conditions and learns colorization by simultaneously predicting color information and semantic information. In addition, we also use a specific color difference loss with characteristics of human visual observation that is combined with semantic segmentation loss and adversarial loss for training. The experimental results show that our method is superior to existing methods in terms of different quality metrics and achieves good results in image colorization.

No abstract

No abstract

Association rule analysis algorithm is widely used in Web log analysis, but the existing association rule analysis algorithm will significantly reduce the analysis and mining performance when the amount of Web log is relatively large. This paper proposes an improved clustering algorithm, which first clusters users with the same interests and hobbies, and then mines association rules for users in the same category, thereby reducing data dispersion. Based on Django’s MVC framework, it optimizes the storage and storage of Web logs. In the analysis part, users can configure the support and confidence of association rule mining through the front-end, and at the same time query the results of mining through Hive, and use encryption algorithms in the data transmission process to ensure data security.

No abstract