模拟钚部件的模板识别

钚部件模板识别技术是深度核裁军的关键核查技术。到目前为止,我们已经开展了模板识别技术的概念研究和对应的模板识别方法的研究,建立了基于均值向量检验法的模板识别技术。这里用数值模拟的方法对所建立的基于均值向量检验法的模板识别技术进行有效性检验。     

模板识别技术在核弹头及其核部件销毁过程中的应用场景和作用

模板识别技术是认证核弹头及其核部件的一项关键技术。模板识别技术是指利用真实核弹头及其核部件的测量数据建立相应的模板，然后利用这些模板，通过特定的比较算法，判断核查对象的类别。图1是模板识别技术在核弹头及其核部件销毁过程中的应用场景假设，虚线表示模板建立的流程，实线表示模板应用的流程。     

类型γ射线能谱指纹的识别机理

放射源的辐射指纹能起到标识和鉴别放射性物体的作用.在涉及核弹头不可逆销毁过程的深度核裁军核查中,核弹头的辐射指纹对标识和鉴别裁减下来的核弹头将起到关键作用.预先研究辐射指纹的有关技术,如识别机理的研究,将有助于深度核裁军的核弹头核查技术发展.以实验室放射源为研究对象,探索了类型γ射线能谱指纹的同一性识别机理.类型γ射线指纹识别机理的研究,就是要找出一种合适的方法,以较高的置信度,描述两个正在进行比较的γ射线指纹是否为同一放射源的指纹.采用了谱形比较法,并用谱相似度概念来描述两个指纹的相似程度.在谱形比较思想的指导下,编制了放射源类型指纹识别软件,并通过放射源同一性的识别实验验证了软件的有效性,同时研究了谱相似度随统计涨落和测量条件,如时间、源强和本底等因素的变化情况.研究结果表明:1)用相似度概念来描述两个指纹的相似程度,回答两个待比较的γ射线能谱是否代表同一类型放射源,是切实可行的;2)该识别机理只具备识别放射源类型的能力,而对同一类型、差异甚微的放射源个体还不能识别 关键词： γ射线能谱指纹 辐射指纹 识别机理 核查技术     

基于多特征的双模板自适应更新跟踪算法

针对均值漂移算法中采用单一颜色特征以及缺乏必要模板更新方法的缺陷,提出一种基于多特征的双模板自适应更新目标跟踪算法。引入像素点邻域灰度均值差和分层空间信息加强目标特征的鉴别性,再通过对目标与背景区域双模板相似度系数的综合分析,准确地判断跟踪干扰因素的来源,并以当前帧目标区域的相似度系数为权值对目标模板进行加权更新,使得模板更新速度与其目标特征变化相适应的同时抑制模板过更新,较好地解决了模板更新时机和更新速度等问题。仿真结果表明,所提算法在不同跟踪场景下均具有较强的鲁棒性。     

核材料γ能谱指纹模糊识别机理研究

以γ射线的能量与强度所构成的二维平面为论域,提出了关于γ射线能谱的二维模糊集合的概念,建立了γ射线能谱二维模糊集合隶属函数.提出和介绍了γ射线能谱指纹模糊识别的基本原理与方法.通过对γ能谱数据的归一化处理,实现了γ射线能谱指纹的类型识别和个体识别.通过引入识别增强因子,获得了较高的识别置信度.对模拟放射性物质的γ射线能谱指纹进行了识别研究,探讨了系统统计涨落以及探测距离变化对识别隶属度的影响.研究表明,γ射线能谱指纹模糊识别方法具有较强的类型识别能力和个体识别能力,可应用于核安全保障等领域. 关键词： γ能谱指纹 模糊识别 核材料     

基于机器视觉的麻将包装识别系统设计

针对麻将包装在实际产线上出现的麻将牌错位、缺失、牌面翻转等问题,基于机器视觉检测技术设计了一套以DM6437处理器为硬件平台的麻将包装识别处理系统。该系统的硬件部分由摄像头板、核心板和接口板三个模块组成,配合机械传动系统来进行识别前后麻将包装的传输。系统的软件部分采用平板Pad对麻将包装进行模板录入,并设计了一套适应于不同机箱内部环境变化的背景剔除方法来完成模板整体分割,以及通过中值计算实现单目标的分离,最后还提出了一种简单高效的混合搜索方式来进行基于SAD的模板匹配。测试结果表明,识别算法对于麻将间有缝隙、麻将整体倾斜、个别或整体麻将翻转、个别麻将位置错乱等问题均能准确判别,模板匹配算法稳定性和适应性较好,识别准确率达95%以上,能满足包装流水线上的缺陷检测。     

基于自适应网络模糊推理系统的γ能谱指纹模糊识别

提出了以自适应网络模糊推理系统参数为识别特征的γ能谱指纹模糊识别方法.通过建模和仿真,提取了γ能谱指纹的模糊系统特征参数,并建立了关于系统特征参数的模糊集及模糊识别原则,以较高的置信度实现了γ能谱指纹的类型识别和个体识别.对实测γ能谱指纹进行了识别,对方法的识别性能进行了研究和探讨.研究表明,该方法不但具有较强的类型识别能力和个体识别能力,并具有较低的识别下限和较强的抗噪声能力.     

基于智能手持设备的车牌识别系统研究

以交警能更加快捷方便地稽查运营车辆为目的,借助最新的移动互联网技术,分析并研究了多种计算机视觉算法。提出了一种基于K均值聚类（K-means）的车牌定位技术,通过颜色的聚类分析来确定车牌区域,定位车牌。又应用垂直投影技术和模板匹配法来分割和识别车牌字符,利用SQlite开发了具有存储车牌字符信息功能的数据库。在此基础上,研制了一套基于智能手持设备的车牌识别系统。功能测试表明,该系统具有良好的性能,能够较好地识别出车牌信息。     

基于模板匹配法的枪械射击准确度验收系统

枪械射击准确度是枪械验收的一项重要指标。为提高验收精度、降低验收成本,针对现有验收方法的不足,提出了光电成像并结合图像处理的验收方法。根据成像的图像特点和验收的实际要求,采用模板匹配算法识别代表瞄准线的十字分划,拟合枪管轴线并用十字分划表示,通过检验两十字之间的角度关系来进行射击准确度的验收。研究结果表明,采用模板匹配算法,十字分划的识别精度小于1个像素,射击准确度验收系统的精度约为0.26 mil。     

基于改进Sobel算子的边缘检测算法的研究

针对传统Sobel边缘检测算法对噪声敏感的缺点进行了分析,提出了自适应权值的改进算法,该权值的大小取决于Sobel算子模板内像素灰度值之和。通过不同形式的噪声图像处理对比,结果表明,该算法不仅计算简单,而且具有较强的抗噪能力,对图像边缘有较高的检验精度,极大地改进了图像边缘识别的效果。     

辐照处理对油菜籽光谱特性影响的研究

针对油菜籽经过核辐照处理后其光谱反射特性会发生改变的特点,提出了应用可见／近红外光谱技术进行油菜籽的快速无损鉴别。利用偏最小二乘法和BP神经网络建立鉴别模型,并比较了不同光谱预处理方法、主成分数据变换方式及隐含层节点数对模型预测结果的影响。实验采用五种剂量辐照(50, 100, 150, 200Gy和不经核辐照处理)的油菜籽共135个样本进行建模,49个进行预测。结果显示,最优模型是原始光谱数据先经过中值滤波平滑法、附加散射校正及一阶求导法预处理。经PLS方法提取6个主成分经自然对数变换后,选取神经网络隐含层结点数为4个或9个。最优模型对是否经过核辐照处理的样本识别率达100%,对核辐照剂量预测精度为85.71%, 说明提出的方法可以用于评估核辐照处理对油菜籽光谱特性产生的明显影响。     

矢量线阵目标调制谱提取及模板生成方法

针对矢量线阵跟踪目标DEMON谱提取问题,提出了一种矢量线阵DEMON谱提取及其模板生成方法.该方法可以有效提取DEMON谱成分,利用DEMON谱互谱可剔除干扰DEMON线谱,较有效解决矢量线阵左右舷目标DEMON谱特征混淆的问题.通过海试数据初步验证了该方法的有效性.     

EASTװ���ڲ������İ�װ׼ֱ

介绍了采用光学仪器结合机械模板的方法完成对EAST装置内部部件的安装准直。通过在平面模板上确定基准孔的方法引入内部部件安装的测量基准,最终的第一壁形状则利用特殊形状的检验模板进行校核,使其达到可接受的位置。     

EAST装置内部部件的安装准直

介绍了采用光学仪器结合机械模板的方法完成对EAST装置内部部件的安装准直。通过在平面模板上确定基准孔的方法引入内部部件安装的测量基准,最终的第一壁形状则利用特殊形状的检验模板进行校核,使其达到可接受的位置。     

基于自适应模板法的脑电信号转移熵分析

脑电信号是一种产生机理相当复杂且非常微弱的随机信号, 综合反映了大脑组织的脑电活动及大脑的功能状态. 由于脑电信号的微弱性, 传统的基本模板方法在脑电信号分析上得到了良好的应用. 为进一步提升分析脑电信号的性能, 提出了一种新的基于自适应模板的转移熵方法并分析了青少年脑电与成年人脑电信号. 结果表明: 对于青少年脑电还是成年人脑电, 与基本模板法相比, 基于自适应模板法的转移熵可以更显著地表示脑电信号的耦合作用, 并且具有更好的区分度, 这将能更好地捕捉到信号中的动态信息、系统动力学复杂性的改变. 同时, 该方法将更有利于医学临床诊断的辅助检测, 对脑电信号是否处于病理状态的诊断提供了新的更好的判断依据.     

Automated inspection of micro-defect recognition system for color filter

This study focused on micro-defect recognition and classification in color filters. First, six types of defects were examined, namely grain, black matrix hole (BMH), indium tin oxide (ITO) defect, missing edge and shape (MES), highlights, and particle. Orthogonal projection was applied to locate each pixel in a test image. Then, an image comparison was performed to mark similar blocks on the test image. The block that best resembled the template was chosen as the new template (or matching adaptive template). Afterwards, image subtraction was applied to subtract the pixels at the same location in each block of the test image from the matching adaptive template. The control limit law employed logic operation to separate the defect from the background region. The complete defect structure was obtained by the morphology method. Next, feature values, including defect gray value, red, green, and blue (RGB) color components, and aspect ratio were obtained as the classifier input. The experimental results showed that defect recognition could be completed as fast as 0.154 s using the proposed recognition system and software. In micro-defect classification, back-propagation neural network (BPNN) and minimum distance classifier (MDC) served as the defect classification decision theories for the five acquired feature values. To validate the proposed system, this study used 41 defects as training samples, and treated the feature values of 307 test samples as the BPNN classifier inputs. The total recognition rate was 93.7%. When an MDC was used, the total recognition rate was 96.8%, indicating that the MDC method is feasible in applying automatic optical inspection technology to classify micro-defects of color filters. The proposed system is proven to successfully improve the production yield and lower costs.     

Template identification technology of nuclear warheads and components

Template identification technology （TIT） is designed for the scenarios where a batch of disarmed nuclear weapons or components would be dismantled to observe a nuclear disarmament treaty. The core function played by the TIT is to make a judgment on whether the verified item belongs to a certain kind of nuclear weapons or component （NW/NC） or to which kind the verified item belongs. This paper analyses the functions played by the TIT in the process of NW/NC dismantlement, and proposes that two phases would be followed when applying the TIT： firstly to establish NW/NC templates with a sample of size n drawn from a certain kind of disarmament NW; secondly to authenticate NW/NC by means of the TIT. This paper also expatiates some terms related to the concept of the TIT and investigates on the development status of NW/NC TIT based on radiation signatures. The study concludes that the design of template structure is crucial to the establishment of an effective TIT and that starting from different research angles and aiming at the same goal of classification different template structures and corresponding template identification methods can be built up to meet specific identification requirements.     

Seeded Ising Model and Distributed Biometric Template Storage and Matching

It is known that a variant of Ising model, called Seeded Ising Model, can be used to recover the information content of a biometric template from a fraction of information therein. The method consists in reconstructing the whole template, which is called the intruder template in this paper, using only a small portion of the given template, a partial template. This reconstruction method may pose a security threat to the integrity of a biometric identity management system. In this paper, based on the Seeded Ising Model, we present a systematic analysis of the possible security breach and its probability of accepting the intruder templates as genuine. Detailed statistical experiments on the intruder match rate are also conducted under various scenarios. In particular, we study (1) how best a template is divided into several small pieces called partial templates, each of which is to be stored in a separate silo; (2) how to do the matching by comparing partial templates in the locked-up silos, and letting only the results of these intra-silo comparisons be sent to the central tallying server for final scoring without requiring the whole templates in one location at any time.     

A robust method for detecting nuclear materials when the underlying model is inexact

This paper is concerned with the detection and identification of nuclides from weak and poorly resolved gamma-ray energy spectra when the underlying model is not known exactly. The algorithm proposed and tested here pairs an exciting and relatively new model selection algorithm with the method of total least squares. Gamma-ray counts are modeled as Poisson processes where the average part is taken to be the model and the difference between the observed gamma-ray counts and the model is considered random noise. Physics provides a template for the model, but we add uncertainty to this template to simulate real life conditions. Unlike most model selection algorithms whose utilities are demonstrated asymptotically, our method emphasizes selection when data is fixed and finite (after all, detector data is undoubtedly finite). Simulation examples provided here demonstrate the proposed algorithm performs well.