目标识别

To fulfill a TV guidance system task of fast recognizing and tracking missile target from sequential images including multiple interferences,a fast segmentation and target characteristic extraction algorithm of sequential images based on binary image index map was proposed.After the sequential images were processed to binary images,a Field Programmable Gate Array was used to scan the binary image once and an index map was built,and then Digital Signal Processing was used to scan the index map once.

针对电视制导系统需从包含多个干扰目标的序列图像中快速识别和跟踪导弹目标的要求，提出了一种基于二值图像索引图的序列图像快速分割及目标特征提取算法，在序列图像二值化后，只需由FPGA对其遍历一次就可得到一张含有目标信息的索引图表，再由DSP对该索引图表边遍历边计算就可得到图像所含目标的数量、面积、质心坐标、二阶矩不变量等特征。

The paper analyses the blood pressure signal with the theory of wavelet and fuzzy recognition. The characters of useful signal are extracted by transform of discrete wavelet and series wavelet and are recognized by the method of fuzzy recognition.

本文首次将小波理论和模糊识别理论相结合，并应用于人体血压波形信号的实际分析中；创造性地将离散小波和连续小波变换结合在一起，完成有用信号的特征提取，并用模糊识别的方法实现目标的识别。

After obtaining an image, the process of filtering, image segmentation, edge searching, interior filling etc., are done, and the target statistic features are extracted.

该方法通过对图片、视频或实时采集的图像进行预处理、目标分割、边界搜索、内部填充等处理后，提取目标的统计学特征，根据目标的特征值和数据库中的已有样本对未知目标进行识别。

Firstly, preprocess road image with edge operator to get the edge information, then construct a deformable template model of road contour and its likelihood function which define the fitting degree for a given group of deformable template parameters, finally genetic algorithm is used to search the global optimal value of the likelihood function to get the optimal parameter of the deformable road model.

真实场景的道路识别算法常常受到光照变化的影响，导致图像序列中道路目标的亮度值变化较大，传统基于固定阈值的方法不能很好的解决该问题，因此道路识别算法鲁棒性差，即使道路检测和识别算法在光照较为固定的场景具有较好的效果，但这样的算法很难移植到其它光照场景。

Well we want computers and cell phones to recognize every word we utter , and yet speech recognition software is,...terrible. Just terrible. And one of the reasons is the way the machines are built is nothing like the way the human brain does it. And so one of the goals we have of course is to use some of the insights from human psychophysics and in particular neuroscience and explore what the consequences are for automatic speech recognition.

我们想计算机和手机识别我们所说的每个字，然而语言识别软件实在是"恐怖，非常的恐怖，其中的一个原因就是机器的建立方式和人类建造机器的方式是不同的"因此我们的目标之一就是我们可以理所当然的使用人类心理和一些特定神经科学的见解并且探索自动语音识别的结果。

This paper provides a new recognition algorithm based on the projective invariant, it can effectively recognize 3D objects from their 2D images and will not be affected by visual angles. It means that this algorithm can recognize deflective characters directly.

本文提出一种新方法——基于射影不变量的识别算法，正是不受视点的影响，可由任意视角的二维图像识别三维目标，即它可以不经过倾斜校正直接识别出歪斜变形的字符。

1On the basis of pattern recognition analysis and in the light of the spectrum oflight source and the spectral response of CCD sensor as well as the spectral reflectance ofkernels,it is found that for the monochromic image recognition system and under the con-dition of reducing the probability error of classification to minimum,the optimum lightsource is a monochromatic light,the wave length of which is that rendering the series re-sponse of the difference between the spectral reflectances of two classes of kernels and theCCD sensor spetral response maximum.

在模式识别理论分析基础上，依据光源光谱、CCD摄像元件光谱响应以及作物籽粒表面反射率光谱特性，在使分类错误概率最小的目标下，得出籽粒黑白图象识别系统最佳光源为单色光，其波长为使两类待识别籽粒反射率光谱差值与CCD光谱响应二者的串联响应最大的波长。

Combining detection and identify of SAR imagery this paper summarized study evolution of SAR image on demising,characters of line and texture extraction, image segmentation and target detection; Introduced up to date study progress; ultimately analyzed program about detection and identify of SAR image in inland and overseas thing and prospected development in future.

本文结合SAR图像检测和识别应用技术的发展过程，综述了SAR图像在噪声抑制、线状特征和纹理特征提取、图像分割和目标检测等方面的研究进展；介绍SAR图像检测和识别的最新研究情况；最后分析当今国内外SAR图像检测和识别所面临的问题，并对未来发展进行展望。

It has provided not only a way of quickly distinguishing between an artificial object and a natural object, but also a way of getting the rough contour curve through the changes in chain code.

提出了利用计算物体轮廓分形维数的方法区分人工目标和自然物体的快速识别方法，给出了通过链码的变换得到待识别目标的轮廓粗糙性曲线的具体算法。

For the machine vision object matching, the feature list correlation algorithm can be adopted in the calculation of the matching similarity measurement.

目标匹配识别中，特征列表相关算法可以有效减少计算时间，匹配具有较高的峰值系数和峰值信噪比，清晰识别目标。

We have no common name for a mime of Sophron or Xenarchus and a Socratic Conversation; and we should still be without one even if the imitation in the two instances were in trimeters or elegiacs or some other kind of verse--though it is the way with people to tack on 'poet' to the name of a metre, and talk of elegiac-poets and epic-poets, thinking that they call them poets not by reason of the imitative nature of their work, but indiscriminately by reason of the metre they write in.

索夫农 、森那库斯和苏格拉底式的对话采用的模仿没有一个公共的名称；三音步诗、挽歌体或其他类型的诗的模仿也没有——人们把&诗人&这一名词和格律名称结合到一起，称之为挽歌体诗人或者史诗诗人，他们被称为诗人，似乎只是因为遵守格律写作，而非他们作品的模仿本质。

The relationship between communicative competence and grammar teaching should be that of the ends and the means.

交际能力和语法的关系应该是目标与途径的关系。