人工识别

Some widely used artificial neural networks such as BP, RBF and ARTMAP were discussed on the common points they shared when solving nonlinear regression problems. A framework, proposed accordingly, suggested that such problems should be implemented in two steps: sample covering and modelbased map regression.

分析了BP、RBF和ARTMAP等人工神经网络在实现非线性映射方面的共同之处，基于RBF等网络对于人脑功能方面的模拟和仿生模式识别的思想，总结出一种处理这类问题的基本框架。

The technology of dactylography has made great progress after more than 100 years development. The organic combination of dactylography with computer arise the automatic system of computer recognition.

经过100多年的发展，指纹学技术取得了长足的进步，现在指纹学与计算机的有机结合，产生了计算机自动识别系统，以前人工比对需要几十个甚至几百个工作日才能完成的任务，利用该系统几分钟就可以完成。

Through research on targets of F 18 aeroplane and the space ship, the advantages of technique of neural network compared with tranditional digit circuit method are proved.

通过对F－18飞机和返回式宇宙飞船两类目标图像进行特征提取、粗编码、训练和分类检测，证明了人工神经网络应用在引信目标成像的识别上相对传统的数字方法具有极大的潜力和优越性。

It is imminently to invent a new method distinguishing the axle temperature intellectively to lighten our burden.

现在迫切需要一种能对轴温进行智能识别分类的方法来减轻人工负担。

This paper systematically provides an overview of recent developments in small punch test technology including empirical and computational methods for determining elasto-plastic parameters from the measured data of small punch test. The computational methods involve finite element and parameter method, inverse finite element procedure, finite element and inverse methodology, inverse identification based on artificial neural networks, finite element optimization, shape deformation and hybrid inverse procedure et al.

本文系统综述小冲杆试验的测量技术及从测量数据来确定材料弹塑性参数的各种经验方法和计算方法，例如有限元分析和参数法、反向有限元法、有限元和反方法、反向识别和人工神经网络、有限元优化和试验变形形状以及杂交反方法等。

This paper describes in brief the lithologic profiles and the geophysical logging curves of the low resistivity oil and gas layers in Tabei area, analyzes the origin of the low resistivity oil and gas reservoirs in that area, and deals emphatically with the principle of applying the neural network to recognizing oil and gas layers, oil-water layers, water layers and dry layers.

简要介绍了塔北低阻油气层岩性剖面、低阻油气层地球物理测井曲线特征，分析了塔北地区低阻油气储层成因，重点论述BP人工神经网络识别油气层、油水同层、水层和干层的方法原理。

In different kinds of automatic recognition technology, it may be the only possible way to replace or partially replace the manual input.

它是一种很方便的汉字输入方法，在各种自动识别输入的方法中，能够代替或部分代替人工输入的唯一可能的方法。

The gas sensitivity did not change significantly after the modification but were somewhat different, such as some are most sensitive to xylene; others are most sensitive to methanal.

本论文也设计了基于各种碳纳米管传感器的电子鼻人工嗅觉系统识别有机气体如苯、甲苯、二甲苯、甲醛。

Second, the conventional linear optimal control can make system stabilize at neighborhood of balance point only. In this paper, we introduced a method of control by Artificial Neural Network. And also, identified variable on line. This method enhanced the adaptability of the control.

其次，由于常规的线性最优控制只能在平衡点附近稳定，这里利用人工神经网络在线识别不同运行状况下的各个参数值，离线训练网络，最后用训练成功的网络进行在线控制，实现了系统的大范围稳定。

In this paper, a method of the Neural Network is proposed for the word recognition.

提出了一种基于人工神经网络的含噪声文字的识别方法。

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。