Search

Abstract With the advent of the screen‐reading era, the confidential documents displayed on the screen can be easily captured by a camera without leaving any traces. Thus, this paper proposes a novel screen‐shooting resilient watermarking scheme for document image using deep neural network. By applying this scheme, when the watermarked image is displayed on the screen and captured by a camera, the watermark can be still extracted from the captured photographs. Specifically, the scheme is an end‐to‐end neural network with an encoder to embed watermark and a decoder to extract watermark. During the training process, a distortion layer between encoder and decoder is added to simulate the distortions introduced by screen‐shooting process in real scenes, such as camera distortion, shooting distortion, and light source distortion. Furthermore, a background sensitive loss and a lpips loss are used to improve visual quality of the watermarked document images in the training process. Besides, a strength factor adjustment strategy is also designed to improve the visual quality with little loss of bit extraction accuracy. The experimental results show that the proposed scheme has higher visual quality and robustness than the other two recent state‐of‐the‐art methods.

Thermochemical conversion of fuels via pyrolysis/carbonization, cracking, gasification and combustion has to involve a number of individual reactions called attribution reactions to form an intercorrelated reaction network for any conversion process. By separating one or some attribution reactions from the others to decouple their interactions existing in the reaction network, the so-called reaction decoupling enables a better understanding of the complex thermal conversion process and further the optimization of the conditions for attribution reactions as well as the entire conversion process to realize advanced performances. The dual bed conversion and two-stage conversion are the two representative types of fuel conversion technologies developed in recent years based on reaction decoupling. Many technical advantages have been proven for such decoupling fuel conversion technologies, such as poly-generation of products, low-cost production of high-grade products, elimination of undesirable products or pollutants, easy operation and control, and so on. The treated fuels with decoupling conversion technologies mainly include solid biomass and coal, as well as liquid petroleum oil. This paper is devoted to reiteration of the reaction decoupling concept and further to reviewing the research, developments and successful applications of several decoupling fuel conversion technologies of two such types by using fluidized bed as their major reactors. Keywords: Reaction decoupling, Fuel conversion, Reaction network, Fluidized bed, Dual bed, Two-stage