基于改进伪中值滤波器的道路图像滤波算法*

针对已有的细胞神经网中值滤波器滤波时,收敛速度慢、稳定性不好以及滤波图像比较模糊的缺点,设计一种差值控制细胞神经网的改进伪中值滤波器。提出了改变取值空间、引入随机扰动、扩大中值滤波窗口尺度和引入Mask掩图的改进方法。实验结果表明：该算法具有去除各种强度脉冲随机噪声能力,又能保护图像细节信息,而且具有良好的实时性。     

CCN activation of oxalic and malonic acid test aerosols with the University of Vienna cloud condensation nuclei counter

The cloud droplet activation of monodisperse laboratory aerosols consisting of single organic and inorganic substances as well as a mixture of several substances was investigated using the University of Vienna cloud condensation nuclei counter (CCNC). The CCNC operates on the principle of a static thermal diffusion chamber. Water vapour supersaturations can be set in the range from 0.1% to 2%. Aqueous solutions of oxalic acid and malonic acid as well as solutions of inorganic compounds (NaCl and (NH₄)₂SO₄) were nebulized in a Collison atomizer and then passed through a closed-loop differential mobility particle spectrometer to produce monodispersed particles. An internally mixed aerosol consisting of ammonium sulphate, oxalic acid and malonic acid with relative concentrations resembling those found in cloud water at a mountain station [Löflund, Kasper-Giebl, Schuster, Giebl, Hitzenberger, Reischl et al. (2002) Atmos. Environ. 36, 1553] was also investigated for cloud condensation nuclei (CCN) activation. All these particles were activated at supersaturations expected from Köhler theory. Oxalic and malonic acid particles are therefore expected to be good atmospheric CCN both as pure particles and as internally mixed particles containing other chemical compounds.     

边缘与区域不一致性引导下的图像拼接篡改检测网络

目的 针对已有图像拼接篡改检测方法中存在的真伪判断分类精度不高、拼接篡改区域定位不准确问题，本文设计了一种篡改边缘两侧和篡改区域内外不一致性引导下的重点关注篡改区域与篡改边缘的图像拼接篡改检测卷积神经网络。方法 图像内容在篡改过程中，拼接物体的边缘都会留下篡改痕迹，这是图像拼接篡改检测的重要线索。因此，本文设计了一条篡改边缘提取分支，通过学习拼接物体边缘两侧的不一致性，重点提取拼接篡改区域的边缘轮廓。考虑到篡改边缘像素点过少会导致网络难以收敛，提出一个边缘加粗策略，形成一个边缘加粗的"甜甜圈"，使得篡改边缘提取结果更具完整性。在不同图像采集过程中，所用相机设备和光线条件等因素不同，导致每幅图像包含的信息也不尽相同。对此，设计了一条篡改区域定位分支，重点学习来自不同图像拼接区域与周围区域之间不一致性的差异化特征，并将注意力机制引入图像拼接篡改检测的篡改区域定位分支，进一步提高对拼接篡改区域的学习关注程度。面向真伪判断设计了一条图像是否经过拼接篡改的二分类网络分支，不但可以快速有效地给出输入图像是否为篡改图像的判断结果，而且可以与上述两条分支的输出结果一起提供给用户，由用户结合视觉语义信息进行综合判断。结果 本文算法与已有的4个代表性方法在4个专业数据集上进行算法实验和性能比较。在真伪判断分类的精确度方面，在Dresden、COCO（common objects in context）、RAISE（a raw images dataset for digital image forensics）和IFS-TC（information forensics and security technical committee）数据集上分别提高了8.3%、4.6%、1.0%和1.0%；在篡改区域定位的准确度方面，F1评分与重叠度IOU（intersection over union）指标较已有方法分别提升了9.4%和8.6%。结论 本文算法将真伪判别分类、篡改区域定位和篡改边缘提取融合在一起，互相促进，较大提升了各分支任务的性能表现，在图像拼接篡改检测方面取得了优于已有方法的效果，为数字图像取证技术领域的研究工作拓展了思路。     

Blind quality assessment for screen content images via convolutional neural network

With the wide propagation of cloud and mobile computing, screen content images (SCIs) have become more indispensable in our daily lives. Compared to natural scene images (NSIs), SCIs possess many particular characteristics, like mixed contents, extremely sharp edges, and text graphics. Consequently, more challenges occur in the feature extraction, which is used to reflect the distortion, during the quality assessment of SCIs. Recently, some convolutional neural network (CNN) models have been designed by automatically learning feature to evaluate the quality. In this paper, we develop a novel blind quality assessment method for SCIs via the CNN. First, compared with existing CNN-based methods, the proposed method avoids the disadvantage of training with image patches, and it is the pioneering attempt that takes the entire image as inputs. Second, instead of the image gray value, the original image is decomposed into two portions, i.e., the predicted and unpredicted portions, according to the internal generative mechanism (IGM) theory as the input of CNN. Through the CNN, all features of the image are learned automatically from beginning to end, and the network finally outputs the predicted score. Since existing SCI database is too small, to fully train the network, we collected 30000 SCIs and employed a high-accuracy full-reference quality assessment metric of SCI to compute scores as the training labels. Experimental results on SIQAD database demonstrate that the proposed method is comparable to reference-based SCI quality assessment metrics and is superior to the state-of-the-art NSI quality assessment metrics.     

Design of data feature-driven 1D/2D convolutional neural networks classifier for recycling black plastic wastes through laser spectroscopy

In this study, two types of convolutional neural network (CNN) classifiers are designed to handle the problem of classifying black plastic wastes. In particular, the black plastic wastes have the property of absorbing laser light coming from spectrometer. Therefore, the classification of black plastic wastes remains still a challenging problem compared to classifying other colored plastic wastes using existing spectroscopy (i.e., NIR). When it comes the classification problem of black plastic wastes, effective classification techniques by the laser spectroscopy of Fourier Transform-Infrared Radiation (FT-IR) with Attenuated Total Reflectance (ATR) and Raman to analyze the classification problem of black plastic wastes are introduced. Due to the strong ability of extracting spatial features and remarkable performance in image classification, 1D and 2D CNN through data features are designed as classifiers. The technique of chemical peak points selection is considered to reduce data redundancy. Furthermore, through the selection of data features based on the extracted 1D data with peak points is introduced. Experimental results demonstrate that 2DCNN classifier designed with the help of 2D data feature selection as well as 1DCNN classifier shows the best performance compared with other reported methods for classifying black plastic wastes.     

Understanding convolutional neural networks with a mathematical model

This work attempts to address two fundamental questions about the structure of the convolutional neural networks (CNN): (1) why a nonlinear activation function is essential at the filter output of all intermediate layers? (2) what is the advantage of the two-layer cascade system over the one-layer system? A mathematical model called the “REctified-COrrelations on a Sphere” (RECOS) is proposed to answer these two questions. After the CNN training process, the converged filter weights define a set of anchor vectors in the RECOS model. Anchor vectors represent the frequently occurring patterns (or the spectral components). The necessity of rectification is explained using the RECOS model. Then, the behavior of a two-layer RECOS system is analyzed and compared with its one-layer counterpart. The LeNet-5 and the MNIST dataset are used to illustrate discussion points. Finally, the RECOS model is generalized to a multilayer system with the AlexNet as an example.     

A Review of FPGA-Based Custom Computing Architecture for Convolutional Neural Network Inference

Convolutional neural network (CNN) has been widely adopted in many tasks. Its inference process is usually applied on edge devices where the computing resources and power consumption are limited. At present, the performance of general processors cannot meet the requirement for CNN models with high computation complexity and large number of pa-rameters. Field-programmable gate array (FPGA)-based custom computing architecture is a promising solution to further enhance the CNN inference performance. The software/hardware co-design can effectively reduce the computing overhead, and improve the inference performance while ensuring accuracy. In this paper, the mainstream methods of CNN structure design, hardware-oriented model compression and FPGA-based custom architecture design are summarized, and the improvement of CNN inference performance is demonstrated through an example. Challenges and possible research directions in the future are concluded to foster research efforts in this domain.     

面向限价指令簿趋势分析的网络集成模型

为了更好地分析限价指令簿(LOBs)的趋势,文中提出面向LOBs趋势分析的网络集成模型(NEM-LOB).模型融合2个长短期记忆(LSTM)子模型和1个卷积神经网络(CNN)子模型.一个LSTM子模型可通过LOBs的分布信息捕捉全局时间依赖性,另一个LSTM子模型可通过LOBs和订单流的动态信息捕捉全局动态性.CNN子模型通过LOBs的事实信息提取局部特征.最后,结合3个子模型,提取特征以获得预测结果.在FI-2010数据集上的实验表明NEM-LOB通过引入订单流信息,能对LOBs进行更好的趋势分析.     

基于 FPGA 的深度可分离卷积加速器研究

设计了一种基于FPGA的低功耗深度可分离卷积加速核;根据PW卷积和DW卷积计算中的共性,采用一种固定乘法阵列通过改变特征和权重输入数据流的方式实现两种卷积的计算结构,最大化DSP的利用率;针对8位非对称量化中符号位可能会溢出的问题,采用符号位单独处理的方法重新封装了双乘法器结构;通过层内7级流水结构保证每个周期数据处理的并行度;在Zynq UltraScale+系列FPGA上成功部署了加速结构;经实验测试,提出的加速结构在提高网络推理速度的同时降低了片上资源的依赖度和整体功耗,原生MobilenetV2在所提FPGA加速器上的平均吞吐率高达130.6GOPS且整体功耗只有4.1w,满足实时边缘计算的要求;相比其他硬件平台,能效比有明显提升;与FPGA上的同类型加速器相比,在性能密度（GOPS/LUT）、功率效率（GOPS/W）和DSP效率（GOPS/DSP）上均有优势。