人工识别

A multi-layer BP neural network, using computer digital image processing and artificial neural network was established in this paper, which could identify the area of diseased spots of soybean laminae.

综合运用计算机数字图像处理技术与人工神经网络技术，建立了一个多层BP神经网络，实现了大豆叶片中病斑的自动识别与特征计算。

Lobata sample were successfully class-identified by back-transmission ANN technology, and the correct rate of forecasting results was 97%, but can not identify between the P.

将样品的近红外光谱，利用误差反向传播人工神经网络技术对葛根与葛藤粉末样品进行了分类识别初探，预测正确率达97.65％。

The macrocyclic polyamines are a kind of excellent ligands and have a substantially high binding affinity with transition metal ions. Macrocyclic polyamine metal complexes as enzyme models are widely used in chemical biology, medicine and gene therapy. 1, 4, 7, 10-tetrazacyclododecane is a representative macrocyclic polyamines compound and shows high binding affinity with transition metal ions, such as Zn, Cu and Co. Their metal complexes especially multinuclear complexes were widely used in DNA, RNA recognition.

大环多胺化合物是一类性质独特的优秀配体，具有良好的金属配位能力，其金属配合物作为人工酶模型广泛应用于核酸结构及功能研究、基因表达与调控、抗癌药物的研制等生物、化学和医学领域。1，4，7，10-四氮杂十二烷是典型的大环多胺化合物，对过渡金属离子Zn， Cu and Co有良好的配位能力，这些金属配合物特别是多核金属配合物被广泛应用于DNA识别中。

Ground penetrating radar have so many advantage, therefore applied very extensive. But now it still exist some proportion to waiting for improvement, for example, distinguishing the GPR diagram primar ily stays in the foundation of the artificial naked eye distinguish and handcraft identify. Therefore it is beneficial to us to understand the electromagnetic wave spreading regulation, and scoop out much more useful information from the GPR wave inside, through forward simulate the familiar penetrating object in physical.

地质雷达具有如此多的优点，故应用十分广泛；但是目前地质雷达亦还有待改进之处，如雷达图像的识别主要还停留在人工的肉眼和手工的基础上；所以对常见探测对象的物理正演模拟，有助于我们了解电磁波的传播规律，挖掘雷达波中更多有用信息。

The parasitizing behavior of the bathyluid Scleroderma guani on the pupa of the yellow mealworm, Tenebrio molitor Linnaeus was investigated in the laboratory. The parasitism process was divided into six stages, i. e. assembling, recognition, stinging, clearing and feeding, oviposition and protecting protelean bathylid.

在人工扩繁条件下观察管氏肿腿蜂Scleroderma guani对中间寄主黄粉甲Tenebrio molitor的寄生行为，其过程可分为：搜寻－识别－螯刺－清理和取食－产卵－护幼。

The protection groups in the copolymers which were prepared previously could be removed and the -NH2 and -OH groups could be reconverted. These high active groups can be used to introduce more bioactive groups and molecules so as to simulate the natural environments of ECM, so the biocompatibilities and cells adhesive capabilities between scaffolds and cells could be improved remarkably.

通过脱除共聚物糖基上的保护基团，还原出-OH、-NH_2，这些高活性的基团为进一步引入具有生物活性的功能基团，实现了对细胞外基质的人工模拟，从而调控材料的细胞识别特性，增强材料生物相容性和改善细胞与材料的黏附特性。

Adaptive control theory,structural parameter identification and error analysis are used to control the construction of pre-stressed-concrete cantilever casting bridge.The construction camber for main beam can be determined by BP artificial neural network.The deflection of main beam should be tested persistently.

对于采用悬臂浇筑施工方法的预应力混凝土桥梁，运用自适应控制理论进行结构参数识别和误差分析；利用BP人工神经网络确定主梁预拱度；在施工过程中对主梁挠度进行连续监测。

First,a landmark model is designed to give position information;second,color segmentation,invariance of cross-ratio and the self-adaptive window are used to detect the artificial landmark,so the position information is got;finally,in order to locate the mobile robot accurately,the binocular stereo vision is used by combining with the position information of artificial landmark.

首先设计了一种可扩展的彩色人工路标，并给出路标的编码方法；然后利用色彩空间变换，直线交比不变性以及自适应窗口实现路标检测与识别；最后在分析双目立体视觉模型的基础上建立起基于路标的双目立体视觉定位模型，实现移动机器人的准确定位。

In chapter one, it compared letters with pictures and showed the importance of observation. In chapter two, it introduced the structure of human eyes and the course of vision. Chapter three introduced the basic key element of vision and the main theories of studying in vision aesthesia. In chapter four, it analyzed the principle of understanding the meaning of a figure according to the theory before, and analyzed the law of aesthetic. Then it explained how people feel the three-dimensional form and the movement, which have offered the theoretical foundation for creating more vivid image. It expounded the purpose and meaning of judging a visual figure in the fifth chapter, and introduced three general standards. It showed a method of judging the figure from different points of view in an example. Summarize to the full text finally, it point out the correct observation of vision image is one of the main ways for people's study, proposed the weak point of this text.

本文在第一章对文字与形象两类视觉信息进行了比较，提出了掌握形象观察方法的重要性；接着在第二章简单介绍了人眼的构造和视觉成像的过程；第三章分别介绍了视觉感知的基本要素和目前研究视觉的主要理论；在第四章，根据感知理论重点分析了人们识别、理解图形意义的原则，并由此归纳总结了形式美感产生的规律，提出了创造生动的视觉形象和构筑立体形象的规则和方法；第五章则阐述了对视觉形象进行评价的目的和意义，介绍了评价的三大普遍标准，针对人工形象提出了一套评价系统，并通过一个实例来说明评价系统的使用过程；最后对全文做出总结，指出正确的认识视觉形象是人们学习的主要途径之一，并提出了本文的不足之处。

Based on the analysis and choosing of factors, a fuzzy recognition neural network BP approach is proposed. It is applied to forecast the freeze-up and break-up date in the Inner Mongolia reach of the Yellow River.

在分析影响凌汛成因因素的基础上，选取合适的预报因子，基于模糊识别人工神经网络BP模型，提出冰凌预报方法，应用于黄河内蒙段封河、开河日期的预报。

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。