為解決電致變色器件的顏色變化受外界環境顏色控制的問題，設計了一種基于單片機的便攜式顏色自適應識別電路。與傳統顏色識別電路相比較，該電路利用數字式的顏色傳感器來獲取外界環境顏色，產生的數字顏色信號易于單片機進行處理。在電路中，下位機部分主要負責獲取電致變色器件變色參數及控制電致變色器件的顏色變化;而上位機部分主要負責把下位機獲取的電致變色器件變色參數進行電壓到顏色的曲線擬合，并通過藍牙通信把擬合曲線參數傳遞給下位機。結果表明，該電路能自動根據環境顏色提供-4~4 V范圍步進為0.1 V的電壓來驅動電致變色器件的顏色顯示，與傳統的顏色識別電路設計相比，識別的精度和速度都得到了明顯改善。
Abstract:
In this paper， a portable adaptive circuit for color identification(PACCI) based on MCU was designed. Compared to the traditional color identification circuit， the PACCI adopts digital sensor to detect the color data from external environment and further generate digital color data， which can be processed easily by MCU. In PACCI， the slave is mainly responsible for detecting the color parameters of the corresponding elcreochromic device and further driving it. For the master， which is mainly responsible for the color curve fitting based on the parameters of the electrochromic device， and transmits the fitting parameters to the slave through the bluetooth device. The results show that the PACCI can provide the basis voltage range from -4V to 4V automatically based on the colors of external environment with step as 0.1V to drive the corresponding electrochromic device. Compared to the traditional color Recognition circuit， the Recognition accuracy and speed of PACCI have been improved significantly.
提出一種基于單片機AT89C51SND1C的MP3播放系統的設計方案。單片機集成了專用的解碼器，使用K9F1208閃存作為外存儲器，放音電路采用CS4330，存儲文件通過播放器上的USB接口設備從PC機上直接下載，液晶顯示采用LCD1602。方案設計簡單，性價比高，低功耗，易擴展。由于采用的是通用單片機實現的，可以很容易地移植到其他微控制器系統中，有很強的市場競爭能力和實用價值。
Abstract:
A MP3 player design based on microchip AT89C51SND1C was presented, which used K9F1208 Flash chip as the memory circuit and used CS4330 as play chip. Storage files were download from PC through USB interfaces player on the device，and the LCD/602 was used as display screen. This system had characteristics of simple design,low power,easy expand，low cost and high Recognition. Using of universual microchip make it easy to transplant to other microcontrol system，and have strong market competitiom and practical value.
Hidden Markov Toolkit (HTK) 3.2.1
HTK is a toolkit for use in research into automatic speech Recognition and has been developed by the Speech Vision Robotics Group at the Cambridge University Engineering Department (http://svr-www.eng.cam.ac.uk) and Entropic Ltd (http://www.entropic.com).
《多傳感器數據融合手冊》
《Handbook of Multisensor Data Fusion》
作者: David L. Hall
定價: USD 199.95
出版社: CRC
出版年: 2001-06-20
簡介 · · · · · ·
Multisensor data fusion is an emerging technology with important applications in both the military and civilian sectors, such as target Recognition, robotics, medical diagnostics, and "smart" buildings. It draws on techniques from wide-ranging disciplines, including artificial intelligence, pattern Recognition, and statistical estimation. This handbook is an up-to-date, comprehensive resource for data fusion system designers and researchers. Top experts in the field lead readers from a basic introduction and survey of data fusion technology to advanced mathematics and theory and to some very practical advice for systems implementers.
Make and answer phone calls
Detect tone and pulse digit from the phone line
Capture Caller ID
Support blind transfer, single-step transfer/conference, consultation transfer/conference, hold, unhold.
Control of the local phone handset, microphone and speaker of the modem
Send and receive faxes
Play and record on the phone line or sound card
Play music in background mode
Silence detection
VU Meter
Wave sound editor that allows your end-users to edit their own sound files.
Voice Recognition and voice synthesis.
Full control over the serial port device
ZModem file transfer utility
File compression and encryption utility
Hidden_Markov_model_for_automatic_speech_Recognition
This code implements in C++ a basic left-right hidden Markov model
and corresponding Baum-Welch (ML) training algorithm. It is meant as
an example of the HMM algorithms described by L.Rabiner (1) and
others. Serious students are directed to the sources listed below for
a theoretical description of the algorithm. KF Lee (2) offers an
especially good tutorial of how to build a speech Recognition system
using hidden Markov models.
Perlbox Voice is an voice enabled application to bring your desktop under your command. With a single word, you can start your web browser, your favorite editor or whatever you want. This is the Linux and Unix voice Recognition solution
我用matlab寫的一個corner detector, 效果比現在流行的harris，susan，CSS等效果要好。
Algorithm is derived from:
X.C. He and N.H.C. Yung, Curvature Scale Space Corner Detector with Adaptive Threshold and Dynamic Region of Support , Proceedings of the 17th International Conference on Pattern Recognition, 2:791-794, August 2004.
Improved algorithm has been included in A Corner Detector based on Global and Local Curvature Properties and submitted to Optical Engineering.
