Convolutional neural network-based methods are attracting increasing attention in steganalysis. However, steganalysis for content-adaptive image steganography in the spatial domain is still a difficult problem. In this paper, a new convolutional neural network-based steganalysis approach was proposed with two contributions. 1) By adding more convolutional layers in the lower part of the model, we proposed a new arrangement of convolutional layers and pooling layers, which can process the local information better than the existing CNN models in steganalysis. 2) By adding the global average pooling layer before the softmax layer instead of using global average pooling before the fully connected layer, the global average pooling was placed in a better position for steganalysis. Two state-of-the-art steganographic algorithms in the spatial domain, namely, WOW and S-UNIWARD, were used to evaluate the effectiveness of our model. The experimental results on BOSSbase showed that the proposed CNN could obtain better steganalysis performance than YeNet across all tested algorithms when the payloads were 0.2, 0.3, and 0.4 bpp.
Gyrator transform has been widely used for image encryption recently. For gyrator transform-based image encryption, the rotation angle used in the gyrator transform is one of the secret keys. In this paper, by analyzing the properties of the gyrator transform, an improved particle swarm optimization (PSO) algorithm was proposed to search the rotation angle in a single gyrator transform. Since the gyrator transform is continuous, it is time-consuming to exhaustedly search the rotation angle, even considering the data precision in a computer. Therefore, a computational intelligence-based search may be an alternative choice. Considering the properties of severe local convergence and obvious global fluctuations of the gyrator transform, an improved PSO algorithm was proposed to be suitable for such situations. The experimental results demonstrated that the proposed improved PSO algorithm can significantly improve the efficiency of searching the rotation angle in a single gyrator transform. Since gyrator transform is the foundation of image encryption in gyrator transform domains, the research on the method of searching the rotation angle in a single gyrator transform is useful for further study on the security of such image encryption algorithms.
In recent years, the trampling events due to overcrowding have occurred frequently, which leads to the demand for crowd counting under a high-density environment. At present, there are few studies on monitoring crowds in a large-scale crowded environment, while there exists technology drawbacks and a lack of mature systems. Aiming to solve the crowd counting problem with high-density under complex environments, a feature fusion-based deep convolutional neural network method FF-CNN (Feature Fusion of Convolutional Neural Network) was proposed in this paper. The proposed FF-CNN mapped the crowd image to its crowd density map, and then obtained the head count by integration. The geometry adaptive kernels were adopted to generate high-quality density maps which were used as ground truths for network training. The deconvolution technique was used to achieve the fusion of high-level and low-level features to get richer features, and two loss functions, i.e., density map loss and absolute count loss, were used for joint optimization. In order to increase the sample diversity, the original images were cropped with a random cropping method for each iteration. The experimental results of FF-CNN on the ShanghaiTech public dataset showed that the fusion of low-level and high-level features can extract richer features to improve the precision of density map estimation, and further improve the accuracy of crowd counting.
MediaCorp Channel 8 of Singapore has produced more than 600 TV series between 1982 and 2006. Based on collecting, viewing and categorizing the representative TV series of MediaCorp Channel 8, this thesis analyzes the six dimensions in the construction of images of ethnic Chinese: Chinese nationals (Overseas Chinese), Singapore citizens, English education, language dialects, new immigrants from China, and other races in Singapore like Malays and Indian. In terms of the images of Overseas Chinese and Singapore citizens, Singapore Chinese TV dramas have demonstrated the transformation of the identities; before the Second World War, the emphasis was on the establishment of the Overseas Chinese identity; after the independence of Singapore, the attention was on promoting and instilling the identity of Singapore citizens. When it comes to English education and language issues, the TV dramas have reflected on English education and criticized the loss of Chinese traditional values. Regarding new immigrants and other races, Singapore's TV dramas have captured the realities of society: the conflicts that the mainstream Chinese have with new immigrants, Malays, and Indians. However, the theme expressed is on the harmonious coexistence of a multi-ethnic and multiracial society. The use of dialects and the struggles of new immigrants in adapting to local society were also presented in these TV dramas from the perspective of promoting social harmony and enhancing social cohesion, which is part of the vision and mission of the Singapore media.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.