对该参数体系进行噪声适应性测试的实验结果表明，无噪声情况下样本识别率为87.50%；
Next, noise compatibility test of this parameter system was carried on. The simulation result was: the sample recognition rate was 87.50% in non-noise condition;
基于粗糙集和神经网络的人脸识别方法是针对PC A方法中存在的高维数问题和它对未训练过的样本识别率低的缺点而提出的。
Face recognition based on rough set and neural network was proposed for the shortcoming of high dimension of PCA face recognition and low recognition rate for non-training samples.
在一个由1013个单词组成的样本中，这个系统的正确识别率达到98.41%，本文也会对这个系统可能潜在的应用加以讨论。
It was found that the system successfully identified 98.41% of words in a sample consisting of 1013 words. Potential applications of this system will also be discussed in this article.
实验结果表明，该调制识别方法在小样本下具有较高的识别率，可以应用在数字信号的调制识别系统中。
The experiment results justify the high recognition rate with less samples, thus the method can be used in the digital signal modulation recognition system.
样本测试实验结果表明，算法具有很高的识别率。
实验表明，该方法对500个未学习样本的识别率达到了95.8%。
Experiments demonstrate that the method achieves a recognition rate of 95.8 % in 500 unstudied samples.
对五百万汉字样本的测试中，应用此引擎的在线词典对有意义短字符串(不包括单字)代码页的识别率可以达到99%以上。
In an online dictionary which used this engineer as a sample, the recognition rate of short string's code pages can reach 99% on the test documents which include about five million Chinese characters.
截集特征提取雷达杂波识别方法所需样本数目少，识别率高，在雷达杂波识别领域具有重要应用。
Compared to other methods, the feature extraction of a truncation set needs fewer samples and has higher recognition rate, which plays an important role in radar clutter recognition.
选用了辽河油区400个碎屑岩层样本对网络进行训练，训练后网络识别率达到96.5%。
The net has been trained through 400 clastic samples in Liaohe Oilfield and its identification rate reaches 96.5 percent.
以常用报纸、杂志正文文本为样本进行实验，字体识别率达到了99%。
Experiments are carried out with samples from newspaper and magazine, the results show that the font recognition rate is 99%.
使用本模型的七个纹理参数作特征，在六类地物类型210个样本上作实验，由此设计的分类器的识别率为98.6%。
Seven texture parameters of this model are used for classifying six types of remote sense image over 210 samples. It's success percent is 98. 6 %.
在OR L人脸库的测试结果表明，在姿态、光照、表情、训练样本数目变化的情况下，该算法都具有较好的识别率。
The experiments on the ORL face database show that the recognition rate of the proposed method is high when pose, illumination condition, face expression and training sample number change.
一种组合方式对于某些样本是提高了识别率，而对于其它样本则可能起到相反的作用。
One combination method can improve recognition rate for some samples but reduce it for others.
弹性匹配具有较高的识别率，但计算复杂度较高，影响了其在大样本库中的应用。
Elastic matching has relatively higher recognition rate but also higher calculation complexity, which limits its application.
用从邮政分拣机上获得的443个信函地址行二值图像样本进行测试，省市一级和市县一级投递地址的正确识别率已经达到了66%。
An experiment on 443 real handwritten address lines is performed. The results show that a correct rate of the sorting area including province and city is up to 66%.
由于识别率较高，造成了正确样本数与错误样本数的比例接近到了8：1。
As the recognition rate is relatively high, the ratio of correct and wrong the number of samples has reached 8:1.
实验结果表明，对训练样本可以达到98.71%识别率，对测试样本可以达到91.37%识别率。
The experiment shows satisfied result. Identify rate can reach 98.71% for training stylebook and 91.37% for testing stylebook.
实验表明，该方法对训练样本可以达到98.71%的识别率，对测试样本可以达到91.37%的识别率。
The experiment show satisfied result. Identify rate could reach 98.71% for training stylebook and 91.37% for testing stylebook.
在ORL人脸库上的实验结果表明，该方法在不提高主分量分析复杂度的情况下，采用较少的特征值提高了单训练样本的识别率。
Simulation results on ORL face databases indicate that the proposed approach (ESWPCA) can achieve higher recognition accuracy with fewer singular values but without the increase of …
通过在覆盖中加入一定数量的异类样本和使用概率的方法来扩大覆盖半径，减少拒识的样本数，提高识别率。
The method of adding some samples of different class and enlarging the coverage radius was used to decrease the number of refused samples and improve the rates of recognition.
SVC算法不仅时间复杂度高，而且在处理分布复杂、不均匀样本时，识别率较低。
SVC not only has a high time complexity but also gets low recognition rate when distribution of the data set is complex and uneven.
当然读者也可以自行用训练样本训练网络，不过要特别注意训练样本的选择，否则可能造成识别率很低。
Of course, the reader can also be its own training network with training samples, but pay special attention to the training samples, otherwise it may result in the recognition rate is very low.
当然读者也可以自行用训练样本训练网络，不过要特别注意训练样本的选择，否则可能造成识别率很低。
Of course, the reader can also be its own training network with training samples, but pay special attention to the training samples, otherwise it may result in the recognition rate is very low.
应用推荐