搜索资源列表
一种基于mfcc语音特征提取方法
- 一种基于mfcc语音特征提取方法,识别率还可以.rar
dtw
- dtw的matlab算法,识别率达到100 。可直接使用或转成c语言代码,下到下位机运行。-dtw' s matlab algorithm to achieve 100 recognition rate. Can be used directly or converted into c language code, run down to the lower machine.
KL
- 基于KL变换的特征提取的方法。 选取数据库中的部分样本(每个人的前5张图片)作为训练样本,其余作为未知的测试样本。从训练样本中得到KL变换矩阵,然后对训练样本和测试样本都进行变换,用变换后的数据作最近邻识别,距离可以为对应灰度值之差的平方和,统计识别率。-KL transform based feature extraction method. Select the database part of the sample (each person' s top 5 pictures)
image similarity
- 图像相似度检测,下面是直方图相交的代码,同种图片的识别率达90%以上,性能非常稳定。 程序的例子是8位(256色)位图,其他位图类似。 -Image similarity detection, the following is the histogram intersection of the code, the same kinds of picture identification rate of 90, performance is very stable. Procedure
ICTCLAS
- 计算所汉语词法分析系统ICTCLAS.分词正确率高达97.58%(973专家组评测),未登录词识别召回率均高于90%,其中中国人名的识别召回率接近98%处理速度为31.5Kbytes/s。ICTCLAS的特色还在于:可以根据需要输出多个高概率结果,有多种输出格式,支持北大词性标注集,973专家组给出的词性标注集合。-Calculate the Chinese Lexical Analysis System ICTCLAS. Segmentation correct rate of 97.58 p
A-Method-Using-Haar-like-and-Skin
- 一种基于肤色和圆角度的手部检测方法,有较高的识别率。-Point of view based on skin color and hand circle detection method has higher recognition rate.
VB6.0-OCR
- 用Visual Basic 6.0编写的OCR识别程序,对数字的识别率高-Optical Character Recognition program by Visual Basic 6.0
zuoye
- 这是opencv的人眼识别程序,经调试可用!识别率很高!-This is the the opencv human eye identification procedures, debugging available! High recognition rate.
tesseract
- OCR 光学字符识别的源码,普通图片的识别率可达百分之九十-OCR optical character recognition source code, common picture of the recognition rate up to 90
ecg
- 能检测心电特征点PQRST,用matlab编写了界面,并能计算识别率-Can detect ECG characteristic points PQRST, prepared with matlab interface, and can calculate the recognition rate
HalconMatch
- 这是本人写的一款基于HALCON形状匹配的源码,识别率比较高,模板客任意制作。-This is my written a source code based on HALCON shape matching, recognition rate is relatively high, the template off any produce.
Text_To_Speak
- 文字识别并朗读输入的文字,识别率较高,是初学者的好帮手-Enter the text to identify and read the text, the higher recognition rate is a good helper for beginners
OPENGL
- OPENGL人脸识别(VC++源代码),使用开源技术OpenCV实现人脸识别,识别率高而精准。-OPENGL face recognition (VC++ source code), OpenCV uses open source technology to achieve recognition, recognition rate and precision.
princomp
- 用于人脸识别,处理图像,识别率很好,基于相位-For face recognition, image processing, based on the phase
4
- 本程序用pca,kpca,svm,pls,fisher实现cstr和csth过程的故障检诊断,检测率为百分之九十九,故障识别率为百分之九十六-The program use pca, kpca, SVM, PLS, fisher realize CSTR process inspection and CSTH fault diagnosis, detection rate was ninety-nine percent, the fault recognition rate is ninety-
adaboostm1code
- 这是一篇关于adaboost.m1算法的人脸识别源码,识别率挺高的,读入任意人脸库即可运行,已经过测试-This is a source code of face recognition algorithm on adaboost.m1 .code has been tested ,you can read face database to run
Tesseract-beta-1.03
- tesseract-1.03 google现在在维护的OCR系统,英文识别率较高。之前由HP开发x-tesseract-1.03 google is now in the maintenance of the OCR system, the English high recognition rate. Developed by the HP before x
TextRecognition
- 该源代码压缩包中有2款OCR手写文字识别源码。一款是陨落雕(ThirdApple)的大作,识别率不错,手写输入识别后分别给出匹配率和匹配的字符。另一款是国外的源代码,也比较简单,这个源代码有字符学习功能,可以先学习,然后识别的能力就增强了。同时该源代码具有识别库文件信息储存,可以把一些个人手写习惯的字符储存起来,这样系统识别效率就高多了。 -OCR
hough
- 图像处理中HOUGH变换检测圆形的代码,识别率比较高-HOUGH transform image processing to detect a circular code, the recognition rate is relatively high
fft
- 用于语音识别前端信号预处理的快速傅里叶变换,提高语音信号识别率!-Fast Fourier transform for speech recognition front-end signal pre-processing, improve the recognition rate of voice signal