中文印刷体文字识别系统ocr

图象处理 功能简单-image processing functions simple!

小球斜抛运动,可以选择小球的高度和角度-oblique throwing the ball movement, the ball can choose the height and angle

这是一个基于卫星通讯的牌照自动识别收费系统，应用平台完全采用VC++开发。-This is a satellite communications-based automatic recognition of license fee system, application platform completely VC++ Development.

文字识别系统，包括文字图象的预处理过程，用visual c++开发，识别率比较高-Character Recognition system, including language and graphic pretreatment process, with visual c development, a relatively high recognition rate

图像处理的北京大学讲义，讲述了图像处理的基础知识-image processing Beijing University lectures, on the basis of image processing knowledge

MSChart是微软发布的.NET 3.5框架下的图表控件，功能强劲，基本上能想到的图表都可以使用它绘制出来，常见的：点状图、饼图、柱状图、曲线图、面积图、排列图等等，同时也支持3D样式的图表显示，给图形统计和报表图形显示提供了很好的解决办法，同时支持Web和WinForm两种方式，不过缺点也比较明显，只能在最新的开发环境中使用，需要.Net 3.5 Sp1以及VS 2008的开发环境。 -MSChart Microsoft released. NET 3.5 framework of the chart control, robust, can basically think of the chart can use it to draw out common: the point-like diagrams, pie charts, bar charts, graphs, area maps, arranged map, etc., but also supports 3D-style graphics display, graphical statistics and reports to the graphical display provides a good solution to support both Web and WinForm in two ways, but the more obvious shortcomings, only in the latest development environment be used need to. Net 3.5 Sp1 and the VS 2008 development environment.

用tc读取屏幕的图形-tc read screen with graphics

数字识别代码 第一步：训练网络。使用训练样本进行训练。（此程序中也可以不训练，因为笔者已经将训练好的网络参数保存起来了，读者使用时可以直接识别）第二步：识别。 首先，打开图像（256色） 再次，进行归一化处理。点击“一次性处理” 最后，点击“R”或者使用菜单找到相应项来进行识别识别的结果显示在屏幕上，同时也输出到文件result.txt中 该系统的识别率一般为90％ 另外，也可以单独对打开的图片一步一步进行图像预处理工作。但要注意，每一步工作只能执行一遍，而且要按顺序执行。步骤为：“256色位图转为灰度图”“灰度图二值化”“去噪”“倾斜校正”“分割”“标准化尺寸”“紧缩重排” 另外注意，要识别的图片，要与win.dat、whi.dat位于同一目录。此两文件保存训练后网络的权值参数 -digital identification code first step : training network. Use of training samples for training. (These procedures also can not training because I have trained network parameters saved, Readers can direct identification) second step : identification. First, open the Image (256 colors) again, to a treatment. Click on the "one-stop" Finally, Click on the "R" or use the menu item corresponding to find the identification of the identification results on the screen, also result.txt output to a file which the system"s recognition rate of 90% for the other, can be individually opened to the step-by-step pictures for image prep

kan jiuxing,大家可以交流一下，共同促进编程水平，欢迎提意见和建议-kan jiuxing, we can exchange that jointly promote programming level, and welcomes comments and suggestions!

8预览视频（预览视频）12 9。视频设置为覆盖模式（启用视频覆盖）12 10。命名捕获文档（命名捕获文件）12