双重JPEG压缩图像篡改区域检测与定位

对JPEG(joint photographic experts group)图像实施篡改往往会产生双重JPEG(double JPEG,DJPE) 压缩痕迹,分析该痕迹有助于揭示图像压缩历史并实现篡改区域定位。现有算法在图像尺寸较小和质量因子(quality factor,QF) 较低的时候性能不佳,对两个QF的组合情况存在限制。本文提出了一种端到端的混合QF双重JPEG压缩图像取证网络,命名为DJPEGNet。首先,使用预处理层从图像头文件中提取表征压缩历史信息的量化表 (quantization table,Qtable) 特征,将图像从空域转换至DCT(discrete cosine transform)域构造统计直方图特征。然后,将两个特征输入到由深度可分离卷积和残差结构堆叠而成的主体结构,输出二分类结果。最后,使用滑动窗口算法自动定位篡改区域并绘制概率分布图。实验结果表明,在使用不同Qtable集生成的小尺寸数据集上,DJPEGNet所有指标均优于现有最先进的算法,其中ACC提高了1.78%,TPR提升了2.00%,TNR提升了1.60%。     

基于自注意力机制和CycleGAN的高分三号ScanSAR图像的扇贝效应抑制

高分三号卫星是我国首颗分辨率达到1 m的C波段 多极化合成孔径雷达(synthetic aperture radar,SAR) 卫星,其中扫描 式合成孔径雷达(scan synthetic aperture radar,ScanSAR)模式是高分三号卫星重要的工 作模式之一,由于该模式的工作机制导致生成的图像可能发生扇贝效应,一般呈现为明暗相 间的条纹。本文针对高分三号卫星ScanSAR模式下存在的扇贝效应,提出自注意力机制与循 环一致对抗网络(cycle-consistent adversarial networks,CycleGAN)结合的模型对Scan S AR图像进行处理,从而抑制扇贝效应产生的条纹现象。本文所示方法与传统扇贝效应抑制方 法和深度学习相关算法进行比较,并通过亮度均值、平均梯度等指标进行分析。实验结果表 明,本文方法可以对高分三号ScanSAR图像存在的扇贝效应进行较好的处理,有效抑制图像 的条纹现象,使得图像质量得到提升,具有较大的实用意义。     

基于改进3D UNet的前列腺MR图像分割

针对前列腺磁共振 (magnetic resonance, MR)图像边缘模糊、对比度较低,灰度值分布不均衡而导致分割精度较差的问题,提出了一种结合双路径注意力(dual path attention,DPA) 和多尺度特征聚合(multi-scale feature aggregation,MFA) 模块的改进3D UNet网络模型。首先,对数据集进行重采样和裁剪处理以适应模型输入。然后,在3D UNet网络的编码器各层引入DPA 并添加残差连接,加强特征的 编码能力。同时,在网络解码器中加入MFA模块,以充分利用空间上下文信息,增强语义信息。最后,在公开数据集PROMISE12上进行验证,所提出的模型的Dice系数为89.90%,Hausdorff 距离为9.37 mm。相比较于其他模型,所提出模型的分割结果更优,且参数量和运算量更少。     

基于余弦-指数混沌映射的分块图像加密算法

为平衡混沌映射中结构与性能的关系,保证加密系统安全性,提出一种基于余弦-指数混沌映射的分块图像加密算法。首先,通过非线性指数项对引入了Tent种子映射的余弦映射进行调制,构造新型余弦-指数混沌映射,并利用SHA-256函数产生与明文相关的密钥,生成随机性较强的混沌序列,实现一次一密;然后,基于拉丁方和位级转换,通过两轮拉丁方索引和比特位拼接,分别设计双重拉丁方和扩展比特位算法,并结合二维约瑟夫序列,对块间预置乱后的明文进行块内置乱,实现不同分块的差异化置乱;最后,基于Zig-Zag变换,采用环状仿Zig-Zag变换设计交叉Zig-Zag变换方法,将中间密文与混沌序列进行双向非线性扩散,实现同时改变像素位置与大小,完成图像加密。实验结果表明,该算法密钥空间大,能有效抵御差分分析和统计分析等典型攻击,具有较好的加密效果。     

基于超像素暗通道和自动色阶优化的图像去雾算法

针对暗通道先验(dark channel prior, DCP)复原图像中的光晕现象、明亮区域色彩失真、环境光估计不准确等问题,提出了基于超像素暗通道和自动色阶优化的单幅图像去雾算法。首先,由改进的White Patch Retinex算法增强图像并计算精确环境光。接着,在传统暗通道去雾算法中引入超像素图像分割和引导滤波算法,使透射率估计的稳健性与精确性得以提升。然后,采用自适应容差对明亮区域的透射率进行补偿,有效抑制明亮区域色彩失真问题。最后,以自动色阶优化算法提高图像对比度。将本文去雾算法与其他算法从主观和客观两个维度进行比较,实验结果表明：采用不同算法对不同浓度的自然雾图进行对比实验,信息熵提高0.2 bit,峰值信噪比(peak signal-to-noise ratio,PSNR)提高0.8 dB,运行效率提高。该算法对不同浓度含雾图像具有良好的适应性,复原图像色彩真实、纹理清晰、细节丰富,去雾效果良好。     

One-Component Artificial Gustatory System Based on Hydrogen-Bond Organic Framework for Discrimination of Versatile Analytes

Hydrogen-bond organic frameworks (HOFs) with excellent structural and luminescent properties have emerged as a promising material for the construction of fluorescence sensors. However, designing a facile, universal and high throughput sensor with multiplex detection capacity still remains challenging. Herein, a one-component sensor array is constructed that mimics natural gustatory system for accurate and high-throughput discrimination and identification of versatile analytes. HOF as a single sensing element greatly simplifies the probe preparation in sensor array and detection procedure. Metal ions, proteins and bacteria as the model targets are rapid and accurately discriminated, presenting the universality of the system. Particularly, the system is successfully used for the classification of antibiotic mechanisms. The study expands the application scope of HOFs and provides a facile and universal system for sensing applications.     

A fixed clustering protocol based on random relay strategy for EHWSN

In Energy Harvesting Wireless Sensor Networks (EHWSN), the communication protocol will directly affect the final performance of the network, so it is necessary to study the communication protocol based on EHWSN. In this paper, for the low-cost fixed clustering problem, a fixed clustering protocol RRCEH is based on random relaying. Our proposed RRCEH abandons the inefficient inter-cluster communication method of the traditional fixed clustering protocol. To coordinate the data upload of the cluster head, RRCEH allocates different random relay vectors to each ring area of the network, and combines all the random relay vectors into a random relay matrix of RRCEH. In each communication round, the cluster head node randomly selects its relay target node to send data according to the probability distribution in the random relay vector in the area. For two different cluster head configuration scenarios, by optimizing the random relay matrix, RRCEH can effectively reduce the network's configuration requirements for cluster head energy harvesting capability, thus reducing the deployment cost of EHWSN.     

Multi-layer and Multi-scale feature aggregation for DIBR-Synthesized image quality assessment

Depth-Image-Based Rendering (DIBR) is one of the main fundamental techniques for generating new viewpoints in 3D video applications such as multi-viewpoint video (MVV), free viewpoint video (FVV) and virtual reality (VR). Due to the imperfections of color images, depth maps or texture restoration techniques, several types of distortions occur in synthesized views. However, most of related works evaluated the quality of DIBR-synthesized views by only detecting a specific type of distortion, such as stretching, black holes, blurring, etc., which were unable to accurately evaluate the quality of DIBR-synthesized views. In this paper, a new no-reference image quality assessment method is proposed to evaluate the quality of DIBR-synthesized images by combining multi-layer and multi-scale features of images. To be specific, the distortions introduced by different stages of virtual viewpoint synthesis are first analyzed, and then multi-layer and multi-scale features are extracted to estimate the degree of texture and structure distortions. As a result, individual quality scores associated with two types of distortions (e.g., structural distortion and texture distortion) are aggregated to an overall image quality. Experimental results on two publicly available DIBR datasets show that the method has better performance than the state-of-the-art models.Index Terms: image quality assessment, DIBR-synthesized image, distortion correction, BIQA.     

Learning knowledge representation with meta knowledge distillation for single image super-resolution

Although the deep CNN-based super-resolution methods have achieved outstanding performance, their memory cost and computational complexity severely limit their practical employment. Knowledge distillation (KD), which can efficiently transfer knowledge from a cumbersome network (teacher) to a compact network (student), has demonstrated its advantages in some computer vision applications. The representation of knowledge is vital for knowledge transferring and student learning, which is generally defined in hand-crafted manners or uses the intermediate features directly. In this paper, we propose a model-agnostic meta knowledge distillation method under the teacher–student architecture for the single image super-resolution task. It provides a more flexible and accurate way to help teachers transmit knowledge in accordance with the abilities of students via knowledge representation networks (KRNets) with learnable parameters. Specifically, the texture-aware dynamic kernels are generated from local information to decompose the distillation problem into texture-wise supervision for further promoting the recovery quality of high-frequency details. In addition, the KRNets are optimized in a meta-learning manner to ensure the knowledge transferring and the student learning are beneficial to improving the reconstructed quality of the student. Experiments conducted on various single image super-resolution datasets demonstrate that our proposed method outperforms existing defined knowledge representation-related distillation methods and can help super-resolution algorithms achieve better reconstruction quality without introducing any extra inference complexity.     

Optimized deep learning-based intrusion detection for wireless sensor networks

The technological innovations and wide use of Wireless Sensor Network (WSN) applications need to handle diverse data. These huge data possess network security issues as intrusions that cannot be neglected or ignored. An effective strategy to counteract security issues in WSN can be achieved through the Intrusion Detection System (IDS). IDS ensures network integrity, availability, and confidentiality by detecting different attacks. Regardless of efforts by various researchers, the domain is still open to obtain an IDS with improved detection accuracy with minimum false alarms to detect intrusions. Machine learning models are deployed as IDS, but their potential solutions need to be improved in terms of detection accuracy. The neural network performance depends on feature selection, and hence, it is essential to bring an efficient feature selection model for better performance. An optimized deep learning model has been presented to detect different types of attacks in WSN. Instead of the conventional parameter selection procedure for Convolutional Neural Network (CNN) architecture, a nature-inspired whale optimization algorithm is included to optimize the CNN parameters such as kernel size, feature map count, padding, and pooling type. These optimized features greatly improved the intrusion detection accuracy compared to Deep Neural network (DNN), Random Forest (RF), and Decision Tree (DT) models.