基于YCbCr肤色模型改进算法及区域特征的人脸检测研究

针对当前人脸检测的研究现状与难题,采用改进的YCbCr椭圆聚类肤色模型进行肤色区域提取,根据肤色在YCb’Cr’空间的分布,对于亮度小于80的非肤色像素点会误判为肤色点,则缩小椭圆聚类;对于亮度大于230的肤色像素点会误判为非肤色点,则扩大椭圆聚类,有效避免了在高亮度区域和亮度较低的区域中的肤色点误判问题。接着利用人脸的几何特征,对二值化图中的目标区域进行比例、大小结构的分析,排除不可能的人脸区域,并基于肤色和位置进行区域优化,将处理后的结果作为候选人脸区域输出。     

基于中值滤波和梯度锐化的边缘检测

实现一种基于中值滤波和梯度锐化的边缘检测方法。首先采用既能过滤噪声又能保护边缘信息的中值滤波对图像进行平滑处理。然后采用梯度锐化加强边缘像素强度,通过简单的二值化获得图像的初始边缘,系统采用连通区域标记的方法去除位于图像封闭边界内的残留黑块。最后通过实验结果与人工提取的结果比较,进行误差分析,找出本文算法的不足之处,以便对该算法进行改进。实践证明,本文的边缘检测方法对含有噪声点且灰度分布比较均匀的图像有很好的效果。     

基于地面先验的3D目标检测算法

为了提高自动驾驶汽车环境感知的性能,增强单目相机对障碍物三维和边界信息的感知能力,提出了一种基于地面先验的3D目标检测算法。基于优化的中心网络(CenterNet)模型,以DLA(deep layer aggregation)为主干网络,增加目标3D边沿框中心点冗余信息预测。根据自动驾驶场景的地面先验信息,结合针孔相机模型,获取目标3D中心深度信息,以优化深度网络学习效果。使用KITTI 3D数据集评测算法性能,结果表明:在保证2D目标检测准确性的基础上,该算法运行帧率约20 fps,满足自动驾驶感知实时性要求;同时相比于CenterNet模型,在平均方位角得分(average orientation score)和鸟视图平均准确率(bird eye view AP)上分别有4.4和4.4%的性能提升。因而,该算法可以提高自动驾驶汽车对障碍物三维和边界信息的感知能力。     

Automatic Channel Detection Using DNN on 2D Seismic Data

Geologists interpret seismic data to understand subsurface properties and subsequently to locate underground hydrocarbon resources. Channels are among the most important geological features interpreters analyze to locate petroleum reservoirs. However, manual channel picking is both time consuming and tedious. Moreover, similar to any other process dependent on human intervention, manual channel picking is error prone and inconsistent. To address these issues, automatic channel detection is both necessary and important for efficient and accurate seismic interpretation. Modern systems make use of real-time image processing techniques for different tasks. Automatic channel detection is a combination of different mathematical methods in digital image processing that can identify streaks within the images called channels that are important to the oil companies. In this paper, we propose an innovative automatic channel detection algorithm based on machine learning techniques. The new algorithm can identify channels in seismic data/images fully automatically and tremendously increases the efficiency and accuracy of the interpretation process. The algorithm uses deep neural network to train the classifier with both the channel and non-channel patches. We provide a field data example to demonstrate the performance of the new algorithm. The training phase gave a maximum accuracy of 84.6% for the classifier and it performed even better in the testing phase, giving a maximum accuracy of 90%.     

Toward in-situ flaw detection in laser powder bed fusion additive manufacturing through layerwise imagery and machine learning

Process monitoring in additive manufacturing may allow components to be certified cheaply and rapidly and opens the possibility of healing defects, if detected. Here, neural networks (NNs) and convolutional neural networks (CNNs) are trained to detect flaws in layerwise images of a build, using labeled XCT data as a ground truth. Multiple images were recorded after each layer before and after recoating with various lighting conditions. Classifying networks were given a single image or multiple images of various lighting conditions for training and testing. CNNs demonstrated significantly better performance than NNs across all tasks. Furthermore, CNNs demonstrated improved generalizability, i.e., the ability to generalize to more diverse data than either the training or validation data sets. Specifically, CNNs trained on high-resolution layerwise images from one build showed minimal loss in performance when applied to data from an independent build, whereas the performance of the NNs degraded significantly. CNN accuracy was also demonstrated to be a function of flaw size, suggesting that smaller flaws may be produced by mechanisms that do not alter the surface morphology of the build plate. CNNs demonstrated accuracies of 93.5 % on large (>200 μm) flaws when testing and training on components from the same build and accuracies of 87.3 % when testing on a previously unseen build. Finally, evidence linking the formation of large lack-of-fusion defects to the presence of process ejecta is presented.     

LearningADD: Machine learning based acoustic defect detection in factory automation

Defect inspection of glass bottles in the beverage industrial is of significance to prevent unexpected losses caused by the damage of bottles during manufacturing and transporting. The commonly used manual methods suffer from inefficiency, excessive space consumption, and beverage wastes after filling. To replace the manual operations in the pre-filling detection with improved efficiency and reduced costs, this paper proposes a machine learning based Acoustic Defect Detection (LearningADD) system. Moreover, to realize scalable deployment on edge and cloud computing platforms, deployment strategies especially partitioning and allocation of functionalities need to be compared and optimized under realistic constraints such as latency, complexity, and capacity of the platforms. In particular, to distinguish the defects in glass bottles efficiently, the improved Hilbert-Huang transform (HHT) is employed to extend the extracted feature sets, and then Shuffled Frog Leaping Algorithm (SFLA) based feature selection is applied to optimize the feature sets. Five deployment strategies are quantitatively compared to optimize real-time performances based on the constraints measured from a real edge and cloud environment. The LearningADD algorithms are validated by the datasets from a real-life beverage factory, and the F-measure of the system reaches 98.48 %. The proposed deployment strategies are verified by experiments on private cloud platforms, which shows that the Distributed Heavy Edge deployment outperforms other strategies, benefited from the parallel computing and edge computing, where the Defect Detection Time for one bottle is less than 2.061 s in 99 % probability.     

Windows Bootkit实现及其检测系统设计

作为新型的劫持系统内核技术,Windows Bootkit具有较强的隐蔽性和免杀能力,引发了严峻的计算机安全问题。通过分析研究Windows Bootkit的实现方式,并结合可信计算检测原理,设计了一种基于可信计算技术的Windows Bootkit检测系统,应用结果表明,该系统能检测出各种形式的Windows Bootkit,可有效增强Windows操作系统下计算机的安全性。     

一种基于网络安全风险评估的入侵检测方法

针对传统的入侵检测系统存在报警数量大、误报率高等缺陷,提出了一种基于网络安全风险评估的入侵检测方法,该方法基于入侵检测结果,引入抗体浓度随入侵强度动态变化这一人工免疫理论的最新研究成果进行网络安全风险的计算,然后根据当前网络面临的实时安全风险动态设置报警策略。实验结果表明,该方法能够实时、定量地计算主机和网络所面临的风险,并极大地降低报警数量和误报率。     

一种基于有向二分图模型和贝叶斯网络的入侵检测方法

针对入侵检测中存在的非确定性推理问题,文章提出一种基于二分图模型和贝叶斯网络的入侵检测方法,该方法利用二分有向图模型表示入侵和相关特征属性之间的因果拓扑关系,利用训练数据中获取模型的概率参数,最后使用最大可能解释对转化后的推理问题进行推理,并通过限定入侵同时发生的数目来提高检测效率。实验表明,该方法具有较高的检测率和很好的鲁棒性。     

入侵检测主流技术及发展动态

入侵检测技术是网络安全的主要技术和网络研究的热点,入侵检测方法包括基于数据挖掘、粗糙集、模式识别、支持向量机和人工免疫等主要技术,详细分析了各种检测方法在入侵检测应用中的优缺点。通过回顾研究人员近期的研究成果,提出了该技术的主要发展方向,为进一步研究提供参考。