搜索资源列表
LIA_RAL_2.0
- 说话人识别工具库,包括说话人识别,语音分离等功能,需要同alize项目结合使用-Speaker Recognition tool library, including speech recognition, voice separation of functions, you need to use the same alize project combines
renlianjiance
- 人脸识别中人脸检测部分的C代码,检测率可达95 。-Face human face detection part of the C code, the detection rate of 95 .
MFCCEX
- MFCC 特征提取。用于语音识别等方面,通过特征提取,然后再进行识别操作-MFCC feature ,using voice recognition
dtmf
- DTMF的产生和识别,内含1234567890*#abcdDTMF码-DTMF generation and recognition, contain code 1234567890*# abcdDTMF
Crowd-Event-Perception
- 基于韦伯场,对监控视频当中的群体异常事件进行自动识别。-Weber field based on the surveillance video which groups automatically identify abnormal events.
HMM-model
- 隐马尔科夫模型是语音识别中的重要算法思想,这里在matlab下实现了一个原理性的算法-Hidden markov models is an important algorithm in speech recognition, here under the matlab implements a rational algorithm
facedetect
- VC6.0,OpenCV实现人脸特征检测 1.实时人脸检测,通过摄像头获取人脸视频流,从中检测头部和眼部位置。这部分鲁棒性较好,光照影响较小2. 在一定程度上能够进行人脸识别,但是识别率不高。 -VC6.0, OpenCV facial feature detection to achieve a real-time face detection, face to get the video stream through the camera, which detects the posit
Audio-Processing
- 音频系统,coding, modulation, AWGN, 通过最小距离探测码元,解码,播放。根据不同的SNR,测试在多小的SNR情况下,人耳能识别音频。-Audio systems, coding, modulation, AWGN, by minimizing the distance detection symbol, decoding, playing. Depending on the SNR, the test in the case of multiple small SNR,
CSharp-call-camera
- C#源码调用笔记本摄像头,便于应用于视频识别与捕获-C# source code to call notebook camera, easy to apply to the identification and capture video
Digital-video-and-audio-technology
- chap02---视频捕捉chap03---视频会议系统chap04---远程视频监控系统chap05---MPEG-4播放技术chap06---MPEG-4编码技术chap07---MPEG-4解码技术chap08---MP3和解码chap14---语音识别系统-Chap02--- video capture chap03--- video conference system chap04--- remote video surveillance system based on chap05-
MyHTMLParser-(2)
- 语音识别,连接到百度的语音库,含有网页解析-Html Parser
voicebox
- 音频处理工具箱,语音增强,语音识别,必要工具箱-Audio Processing Toolbox speech
enframe
- 通过对音频文件进行分帧,从而可以对音频文件进行处理和识别。-By framing the audio file, the audio file which can be processed and recognized.
code
- 这是一些有关做车流量里的车牌识别时用到的视频,用这些适配可以判断你的代码是否有误。-a simple picture
VideoSystem
- 自动识别视频采集设备,用户定制获得视频采集设备支持的格式,用户定制视频采集设备输出的格式-Automatic identification of video acquisition device, users to customize the format of the video collection equipment support, custom video acquisition device output format
yinzhang
- 印章识别:使用支持向量机(SVM)进行分类,把印章和背景区分,以分离印章。-using the SVM to recognizing a stamp from its background
handdelectKalmen
- kinect Kalmen识别 使用opencv openni-kinect Kalmen recognition using opencv openni
yhj
- 视频监控中车型识别代码,自己写的,希望和大家多多交流-Vehicle identification code in video surveillance, write myself, and we hope more exchanges with you
intelligent-house
- 程序包含数据采集与数据分析部分、电话交换网程控交换信令识别与分析部分、GSM模块TC35 modem接口程序部分、分析控制部分。-Program includes data acquisition and data analysis part of the program-controlled telephone switching network identification and the analysis of signaling exchange, GSM module TC35 mo
pocketsphinx-0.8.tar
- CMU大学的pocket-sphink 0.8 源码资料,对研究语音识别有很大帮助,这是轻量级的sphinx,可以应用到嵌入式设备中 -Pocket-sphink CMU University 0.8 source data, the study of speech recognition helps a lot, which is lightweight sphinx, can be applied to embedded devices