Xilinx LUT

基于openCV得高斯背景模型提取。需要openCV，内置测试视频-OpenCV based on a Gaussian background model extraction. Need openCV, built-in test video

Visual c++编写主机端虚拟频谱显示仪！-Visual c++ to prepare the host-side virtual spectrum displays!

应用背景机器视觉中，图像处理算法很多，但是大都处理复杂，我看了大量算法提取出一套比较简单有效的跟踪算法。基于opencv库函数对图像的强大处理能力和卡尔曼滤波原理的精妙，算法效果明显。欢迎大家借鉴使用，有意机器视觉学习的朋友欢迎提出建议。关键技术主要是利用opencv对图像的处理，灰度化，二值化，然后进行轮廓识别加上方框标记，最后利用卡尔曼滤波跟踪。关键思路是对提取出的多个轮廓进行最大值选取，从而确定跟踪点，为卡尔曼滤波的使用提供接口。为防止找不到最大轮廓的bug还设计了一个小算法。

VC++6.0的实时曲线图表程序.随着输入数据的变化,图表曲线随之实时的上下波动.-VC 6.0 real-time graphs procedures. Along with the changes in input data, Real-time charts followed the curve fluctuations. -VC++ 6.0 real-time curve of the chart procedures. With the input data changes, subsequent real-time charts curve fluctuated .- VC 6.0 real-time graphs procedures. Along with the changes in input data, Real-time charts followed the curve fluctuations.

这是DCT的改进算法，可以提高DCT算法的执行速度。-This is the DCT of the improved algorithm can improve the execution speed DCT algorithms.

图像标定的源代码，可以参考下我得做法，我毕业设计的内容-Image calibration source code, can refer to the next I have to practice, I graduated from the design of the content

256色位图的 Huffman 编码-256-color bitmap Huffman coding

用java实现的三维控件内立方体的各种几何变换，如”旋转“，”缩放“”平移“等。-used to achieve the three-dimensional cube within the control of various geometric transformation, as "revolving", "zoom", "Translation."

利用opengl技术和位图显示，模拟了三维地形的生成-Technology and the use of opengl bitmap to simulate the generation of three-dimensional terrain

目前该手写体识别系统主要分为 预处理模块： 主要包括训练数据和识别数据的读取，归一化，二值化 特征提取模块：主要包括笔划方向特征和网格密度特征，还可以根据对识别率的要求继续增加其他特征 识别（分类器）模块：主要包括SVM方法和BP神经网络的方法，其中SVM方法的识别率较高，SVM＋网格密度特征， 在小字符集情况下，达到了识别率97％以上 采用OO思想编写，适合做二次开发-currently the handwriting recognition system consists of pretreatment modules : including training data and identification data read, in one, two values of feature extraction module : the main characteristics of the direction including strokes and grid density characteristics, but also based on the identification of the requirements to continue to increase other identification ( Categories) modules : include SVM methods and BP networks, which SVM method for the identification of high SVM+ mesh density characteristics, in a small set of characters to achieve a recognition rate of over 97% using OO ideological preparation, suitable for secondary development