基于卷积神经网络的高相似度图像识别方法

考虑到部分图像中的相似度较高,会造成错误的图像分类或图像混淆。为了满足对高相似度图像的识别需求,提出一种基于卷积神经网络的高相似度图像识别方法。根据高相似度图像的预处理,计算图像特征的相似度加权和,通过构建高相似度图像特征的频数直方图,检索高相似度图像特征的相似度。基于神经元中图像特征之间的灵敏度,建立误差函数,结合采样层中图像特征的灵敏度,更新卷积神经网络的权值。利用迭代分析法,确定图像的中心点,以中心点为判定条件,实现高相似度图像的识别。实验结果表明,文中方法能够识别出具有较高相似度的图像,并提高图像的识别效率。

结合高色彩相似度预处理的压缩域隐写算法

为提高图像隐写算法的载荷能力,增强载体的嵌入容量,提出一种结合高色彩相似度预处理的压缩域隐写算法。对图像进行预处理,利用超像素分割(SLIC)将图像根据内容进行分块,该分块方式具有空间接近度低、色彩相似度高的特点,增强图像的载荷能力;利用改进后的AMBTC压缩编码算法对形状和大小不规则的超像素块进行重新编码并嵌入秘密信息。通过设计率失真实验和有效性实验,验证了该预处理算法对提高嵌入容量的有效性。

高相似度英语词语自主选取系统设计

针对传统的基于支持向量机的高相似度英语词语自主选取系统一直存在选取效果差、精度低的问题,提出一种基于数据挖掘的高相似度英语词语自主选取系统设计方法。首先根据英语词语的相似度概念,计算出两个英语词语义项的最短路径与其距离最近的公共父节点之间的深度。利用数据挖掘法将英语词语文本特征选择转换为一个多目标优化问题;然后以英语词语特征维数最少、分类正确率相对最高为选取标准,采用蚁群算法找到英语词语的最优特征子集;最后通过建立神经网络分类器完成高相似度英语词语自主选取系统设计。实验结果证明,所提方法可以精确地选取出高相似度英语词语,且选取时间较短,实用性广泛。

密集堆叠下的高相似度木块横截面检测

快速有效地检测和获取木块横截面信息,是提升木块生产交易效率的关键。由于木块往往被密集堆叠、木块横截面相似度高且边界不明显,给检测木块横截面信息带来了较大的挑战。针对密集堆叠下的高相似度木块横截面检测困难,本文提出了简单高效的Wood R-CNN网络模型,通过改进模型的损失函数和非极大值抑制算法来提升检测精度,简化网络结构和改进特征金字塔网络来保证检测速度。实验证明:该模型可在密集堆叠情况下精确地检测高相似度木块横截面,检测速度较快且鲁棒性良好,可实际运用于木块生产和交易中。

多型号复杂轮廓零件视觉识别技术在汽车制造业中的应用

考虑到多型号、多变形、相似度高的零件,针对如何实现设备自动防错,提出使用视觉检测系统,通过多模式串行的检测逻辑设计和阈值设计,让设备实现零件自动检测具有防错功能,设备不但自己动起来还能自动判断产品是否合格,真正意义上实现自动化。根据检测硬件需要结合生产实际条件,搭建检测系统,设计检测方案、HMI界面和软件程序。经过实际应用验证该系统状态稳定,防错功能可靠,有效解决了困扰汽车行业的多型号、复杂轮廓、高相似度零件自动防错的难题。

改进形态学相关算法以识别高相似度灰度图像

从形态学角度定义了灰度联合图像相似度 ,提出两种基于位表示法形态学相关算法的改进算法 ,通过提取位表示法的图像片边缘特征或二元化位表示法的图像片功率谱 ,以提高位表示法形态学相关算法对高相似度灰度图像的识别能力。

Study and Application of Fingerprints of Ginkgo biloba Leaves Preparations

Aim To establish a method for determination of Ginkgo biloba L, its extractand preparations with HPLC fingerprints, so as to control the quality of the preparations. MethodsHPLC-DAD method was used to determine the constituents in preparations. Diamonsil? C_(18) (200mm X 4.6 mm, 5 μm) was used as analytical column, and acetonitrile/KH_2PO_4 was used as mobilephase with gradient elu-tion. The column temperature was at 24 ℃. The HPLC profile of chemicalconstituents of control sample and preparations were analyzed using similarity software. Results Thefingerprints of different preparations from different companies were slightly different because ofthe different preparing procedures. Mean while, the fingerprints of different batches of the samepreparation from the same company were similar to each other and the technology of each preparationwas stable. Conclusion This method is accurate, reproducible , simple, and can be used as ananalytical method for the routine quality control of Ginkgo biloba preparations.

Similarity measure design for high dimensional data

Information analysis of high dimensional data was carried out through similarity measure application. High dimensional data were considered as the a typical structure. Additionally, overlapped and non-overlapped data were introduced, and similarity measure analysis was also illustrated and compared with conventional similarity measure. As a result, overlapped data comparison was possible to present similarity with conventional similarity measure. Non-overlapped data similarity analysis provided the clue to solve the similarity of high dimensional data. Considering high dimensional data analysis was designed with consideration of neighborhoods information. Conservative and strict solutions were proposed. Proposed similarity measure was applied to express financial fraud among multi dimensional datasets. In illustrative example, financial fraud similarity with respect to age, gender, qualification and job was presented. And with the proposed similarity measure, high dimensional personal data were calculated to evaluate how similar to the financial fraud. Calculation results show that the actual fraud has rather high similarity measure compared to the average, from minimal 0.0609 to maximal 0.1667.

Method for obtaining high-resolution velocity spectrum based on weighted similarity

Seismic wave velocity is one of the most important processing parameters of seismic data,which also determines the accuracy of imaging.The conventional method of velocity analysis involves scanning through a series of equal intervals of velocity,producing the velocity spectrum by superposing energy or similarity coefficients.In this method,however,the sensitivity of the semblance spectrum to change of velocity is weak,so the resolution is poor.In this paper,to solve the above deficiencies of conventional velocity analysis,a method for obtaining a high-resolution velocity spectrum based on weighted similarity is proposed.By introducing two weighting functions,the resolution of the similarity spectrum in time and velocity is improved.Numerical examples and real seismic data indicate that the proposed method provides a velocity spectrum with higher resolution than conventional methods and can separate cross reflectors which are aliased in conventional semblance spectrums;at the same time,the method shows good noise-resistibility.

Cloud model-clustering analysis based evaluation for ventilation system of underground metal mine in alpine region

Ventilation system is significant in underground metal mine of alpine region.Reasonable evaluation of ventilation effectiveness will lead to a practical improvement for the maintenance and management of ventilation system.However,it is difficult to make an effective evaluation of ventilation system due to the lack of classification criteria with respect to underground metal mine in alpine region.This paper proposes a novel evaluation method called the cloud model-clustering analysis(CMCA).Cloud model(CM)is utilized to process collected data of ventilation system,and they are converted into cloud descriptors by CM.Cloud similarity(CS)based Euclidean distance(ED)is proposed to make clustering analysis of assessed samples.Then the classification of assessed samples will be identified by clustering analysis results.A case study is developed based on CMCA.Evaluation results show that ventilation effectiveness can be well classified.Moreover,CM is used alone to make comparison of evaluation results obtained by CMCA.Then the availability and validity of CMCA is verified.Meanwhile,difference of CS based ED and classical ED is analyzed.Two new clustering analysis methods are introduced to make comparison with CMCA.Then the ability of proposed CMCA to meet evaluation requirements of ventilation system is verified.

Research on Semantic and Cache Model of Relational Database

The paper firstly analyze cache replacement strategies at present, and proposed the ideas of the semantic query cache replacement based on user access features, and describe the semantic similarity calculation and realize the algorithm of replacement strategy. The strategy use semantic to match information in the query cache, through dynamic analysis and tracking three characteristics of user access time, user access to content and Business Association, give out the similarity minimum of the cache item, to improve the hit ratio of the cache and the response time and throughput of the server is improved.

基于偏振成像技术的空间大气偏振模式分布获取

根据仿生偏振导航对天空偏振模式信息的需求,设计实现了一种利用具有180°视场的鱼眼镜头构建的偏振成像系统采集天空偏振信息,并将采集得到的平面二维偏振模式经Matlab程序处理后还原为空间偏振模式分布,从偏振成像理论进行分析,并对所需要的实验设备进行标定,得到了实验中鱼眼镜头的成像公式及参数,并对所采集的图像进行视场校正。标定与校正后所得空间偏振模式分布与单次瑞利散射理论模型保持一致,且具有较高的相似度,其中偏振方位角相似度可达82.4%,偏振度相似度可达96.91%。