搜索资源列表
OCRUtil
- java实现tesseract—OCR,是实现抓取图片中的文字,识别率基本上达到85 ,由于tesseract的汉化包有50m左右,故要用的请自行到tesseract官网上下字啊对应的汉化包-java for tesseract—OCR
recognizition
- 本段程序实现简单验证码的分割,提取和识别,达到了较高的识别率-recognize simple CAPTCHA
chmm
- 数字0-9的语音识别实现,采用双门限端点检测算法,mfcc和lpcc相结合的特征参数提取,识别率较高。-Numbers 0-9 of speech recognition, adopts double threshold endpoint detection algorithm, the combination of MFCC and LPCC feature parameter extraction, the recognition rate is higher.
Identifyamovingobject
- 鉴别一个移动物体,可以实现锁定目标 识别率很高,可以供大家学习 -Identify a moving object, can realize the target recognition rate is very high, can be for everybody to learn
QRRecognition
- 二维码识别程序,可直接在VB中使用,引用方便,识别率高-Two-dimensional code recognition procedures can be directly used in VB, ease of reference, the recognition rate
RSC
- RSC实现人脸识别,使用PCM降维并且采用gabor滤波器来提高识别率-RSC face recognition, using the PCM dimensionality reduction and the use of gabor filter to improve the recognition rate
123MNISTTrain
- 手写数字训练识别,基于MNIST库进行训练识别,6W个训练样本,识别率95 以上-Handwritten numeral recognition training, training on MNIST library identification, 6W training samples, the recognition rate of 95 or more
cpjqdwym
- 车牌精确定位,定位精度大于99 ,非常值得参考,能够有效提高车牌识别率-Plate precise positioning, positioning accuracy is greater than 99 , a very good reference, can effectively improve the rate of license plate recognition
enddect
- 语音端点检测实验程序,利用短时能量和过零率检测,具有较高的识别率-Speech Endpoint Detection experimental procedures, the use of short-term energy and zero-crossing rate of detection, has a higher recognition rate
PCAFaceRec
- 基于ORL人脸库的人脸识别源程序,识别率88%。-Based on the ORL face database for face recognition source code, the recognition rate of 88.
gmm
- 基于GMM的说话人识别,搭建了一个说话人识别系统用于试验测试,验证了一些参数对性能 的影响,同时使用了多线程并行处理技术,以此缩短识别时间:并提出了一种放 大特征向量差距,变换特征向量在特征空间的分布来提升大容量语音库中说话人 识别率的方法。 -GMM-based speaker recognition, to build a speaker recognition system used for pilot testing to verify the performance i
shibielv
- 人脸识别识别率的仿真结果 -Face recognition identification of the simulation results of the simulation results of the recognition rate
tesseract-ocr
- 用于图片识别,支持中英文,用于android手机客户端,识别率高-For image recognition, support in English, for android mobile client, a high recognition rate
PCA
- 针对稀疏表示识别方法需要大量样本训练过完备字典且特征冗余度较高的问题,提出了结合过完备字典学习与PCA降维的小样本语音情感识别算法.该方法首先用PCA降维方法将特征降维,再将处理后的特征用于过完备字典训练与稀疏表示识别方法,从而给出了语音情感特征的稀疏表示方法,并确定了新算法的具体步骤.为验证其有效性,在同等特征维数下,将方法与BP, SVM进行比较,并对比、分析语音情感特征稀疏化前后对语音情感识别率、时间效率以及空间效率的影响.试验结果表明,所提出方法的识别率比SVM与BP高 与采用稀疏化前的
pangusegment-63555
- 用于实现盘古分词 可以同时实现完整拼音和首字母的转换,识别率比较高,扩展后可以进行各项应用,特别推荐给大家 App_code下StrToPinyin.cs和ConvertHzToPz_Gb2312.cs分别为拼音首字母缩写和全拼转换函数-Used to implement the pangu participle Can achieve complete the transformation of the initials of the pinyin and at
recognize-letters
- 这是一个VC++程序,能识别手写体字母和打印体字母,识别率90 -To recognize the handwritten and printed letters
BpNet-Recognize
- 基于神经网络的字符识别,功能强大,识别率高,是学习字符识别不错的资料。-Base on Bpnet, itis very
face
- 人工智能人脸识别系统,计算识别率,采用最传统的方法-Artificial Intelligence- face recognition system, recognition rate is calculated, using the most traditional methods
face-recognition
- 基于Yale人脸数据库的人脸识别,识别率达到90.67 -The face recognition based on Yale face database,and the the recognition rate is 90.67
bp
- BP网络对不同图像的识别程序,达到较高的识别率,可供参考。-BP network for different image recognition procedures to achieve a high recognition rate, for reference.