人工识别

The second part of this thesis mainly deals with the classification problems of heavy element atomic spectral energy levels.

本文的第二篇论述了将模式识别-人工神经网络方法的PCA-BPN（主成分分析-反传神经网络）和PLS-BPN应用于CmⅠ、UⅠ、CmⅡ等重元素原子光谱能级的分类研究工作，明确指认了许多前人应用早期模式识别方法以及CPN方法无法确认或错误指认的未知能级所属的电子组态，取得了较好的效果。

At last, a comprehensive identification method of control chart pattern is suggested, and an application is given.

接着，研究了两类控制图模式识别的方法：包括基于规则的和基于人工神经网络的控制图模式识别方法。

Euler-Bernoulli beam model was employed in forced vibration analysis of strongly coupled beam system by using finite element method.

在反问题中，利用基于时域响应的有限元模型修正法进行了强耦合梁系统局部损伤的识别，讨论了人工测量噪声对损伤识别结果的影响。

The text introduces four types of profit window dressing in statements firstly, drawing lessons from knowledge of experience of manual work, basing on the structure of "The Statement of Profits and Lots", sums up ten important financial indicatrix , which is used as the method to complete the judging process of the types of profits window dressing in accounting theory in advance.

本文从介绍会计报表利润粉饰四种基本类型的特征入手，借鉴人工经验、依据《利润表》的结构关系，研究总结出十个重要的识别会计报表利润粉饰的财务指标，依指标数值的变动关系从理论上先行完成识别报表利润粉饰类型的判断过程。

Finally, with the help of a learnable artificial neural networks, most of the 3D features of a model could be recognized.

最后，再利用人工神经网络的学习与识别能力识别出模型的特徵。

This thesis was Carried out basing on the Seals Automatically Reorganization project in a Information Science Company of ChongQing municipalization.

摘要本文的研究工作是结合市内某信息科技公司的"印鉴自动识别系统"研发项目开展的，作者在深入分析了人工神经网络的各种数学模型及算法的基础上，重点剖析了前馈神经网络的算法思想，对其进行了实用、有效的改进，并将它成功的应用于"图象识别技术"，取得了较为满意的成果。

This thesis was Carried out basing on the Seals Automatically Reorganization project in a Information Science Company of ChongQing municipalization. In the paper, based on the analyzing of the mathematical models and their algorithms of kinds of Artificial Neural Networks, the author analyzed the algorithm of the Back-Propagation networks model, at the same time, the author improved the algorithm practically and effectively, and applied it in the recognition technique of digital image successfully.

本文的研究工作是结合市内某信息科技公司的"印鉴自动识别系统"研发项目开展的，作者在深入分析了人工神经网络的各种数学模型及算法的基础上，重点剖析了前馈神经网络的算法思想，对其进行了实用、有效的改进，并将它成功的应用于"图象识别技术"，取得了较为满意的成果。

Artificial neural network is applied in pattern recognition of the ratio of hydrogen to nitrogen of a nitrogenous fertilizer plant.

用人工神经网络对某氮肥厂合成工段的氮氢比进行模式识别，识别准确率达到100％。

As to the abuse of checking and recognition completed by man after the character pressed and as to the information recorded of product by producer, subject of automatic recognition protuberant character was proposed.

针对标牌压印结束之后的合格检测以及生产厂家对产品信息的录入都靠人工检查和识别来完成的这一弊端，提出实现标牌凹凸字符自动识别的研究课题。

Artificial mark recognition,including mark area recognition and mark pattern recognition,is a significant process of augmented reality.

人工标志识别包括标志区域识别和标志图案识别，它是实现增强现实的重要步骤。

The absorption and distribution of chromium were studied in ryeusing nutrient culture technique and pot experiment.

采用不同浓度K2CrO4(0，0.4，0.8和1.2 mmol/L)的Hoagland营养液处理黑麦幼苗，测定铬在黑麦体内的亚细胞分布、铬化学形态及不同部位的积累。

By analyzing theory foundation of mathematical morphology in the digital image processing, researching morphology arithmetic of the binary Image, discussing two basic forms for the least structure element: dilation and erosion.

通过分析数学形态学在图像中的理论基础，研究二值图像的形态分析算法，探讨最小结构元素的两种基本形态：膨胀和腐蚀；分析了数学形态学复杂算法的基本原理，把数学形态学的部分并行处理理念引入到家实际应用中。