搜索资源列表
lingyun_asr_server.cpp.tar
- 灵云语音识别,完成音频到文字的转换,处理pcm格式-convert audio to text
demo_linux_x64
- linux手写识别引擎,主要是64位的,我试过了可以用,arm版的官网有-Linux handwriting recognition engine, mainly 64-bit, I tried to use, arm version of the official website
TrafficSign
- codeblocks Linux 交通标识识别-codeblocks Linux Traffic sign recognition
vxi-11
- 实现LXI仪器的发现与识别功能,该功能是基于VXI-11协议-To achieve LXI instrument discovery and recognition functions,This feature is based on the VXI-11 protocol
TCS3200--coulaur-reg
- tcs3200 颜色识别 能识别五种颜色 stm32 代码-tcs yanseshibie nengshibie wuzhogn yanse
EndPoint
- 语音端点检测,刚打了飞机的考拉法国大的放大范德萨发(voice endpoint by c++,coiodjogj;agldfhkgk;alfjdo;ashkgdf)
hi_gpio.tar
- hi3518e控制LED,识别按键的驱动与测试程序(Hi3518e control LED to identify key drivers and test programs)
最大熵印度尼西亚语代码
- 用于实现NER的功能,其中各种功能以及任务齐全,可以直接运行使用(used for the NER task)
traffic-sign-detection
- 实现场景中标志的检测,能够用OpenCV将结果显示输出。(Realize the detection of flag in scene)
WEGASUN-M6语音识别模块资料包2017-6-19
- 裸机编程,实现led灯的读写,使用TQ210开发版(Baremetal programming)
81928140
- PLC程序根据定义的通信协议(即 PLC接收信息 帧的格式和定义 )识别其信息 内容,通过PC 的 COM1与S7-200()
2014220303020_yang_lab1
- 一个可以读出“test.html”的程序,该程序能够识别brand(品牌),price(价格),capacity(容量)等信息,并命名此程序为“man_lex.c”(A program that can read "test.html" can recognize brand (brand), price (price), capacity (capacity) and other information, and named this program as "ma
googLeNet.tar
- 有googlenet网络模型的实现,和googlenet网络结构图,实现物体的识别与分类(The realization of the googlenet network model and the googlenet network structure diagram to realize the recognition and classification of the objects)
pcm.tar
- 在FPGA开发板上实现通信中PCM30/32系统的时分复用,编码,解码,串并行转换,以及同步识别(On the FPGA development board, we complete time division multiplexing, encoding, decoding, serial parallel conversion and synchronization identification of PCM30/32 system in communication.)
apache-eagle-0.4.0-incubating-src.tar
- 开源的数据分析解决方案,用于在大数据平台(如HADOOP1、SARK2、NoSQL等)上立即识别安全性和性能问题 分析数据活动、纱线应用、JMX度量和守护进程日志等,提供了-艺术警报引擎,以识别安全漏洞,性能问题。(Apache Eagle (called Eagle in the following) is an open source analytics solution for identifying security and performance issues instantly o
adafruit-pi-cam-master
- 树莓派 OPENCV打开摄像头 人脸识别(Raspberry pie OPENCV open camera face recognition)
FaceRecoginition
- 基于opencv与python的人脸识别程序
dtw
- 可以用来实现dtw。在孤立词语音识别中,最为简单有效的方法是采用DTW(Dynamic Time Warping,动态时间归整)算法,该算法基于动态规划(DP)的思想,解决了发音长短不一的模板匹配问题,是语音识别中出现较早、较为经典的一种算法,用于孤立词识别。HMM算法在训练阶段需要提供大量的语音数据,通过反复计算才能得到模型参数,而DTW算法的训练中几乎不需要额外的计算。所以在孤立词语音识别中,DTW算法仍然得到广泛的应用。(Can be used to implement DTW)
keras-yolo3-master
- yolo的实时车辆检测与识别,keras-yolo3-master(YOLO real-time vehicle detection and identification, keras-yolo3 main)