资源列表
PrintScreenTemp
- 后台运行; 对正在运行的前台程序桌面程序指定位置截图,拼接,图像识别后获得监控数据,保存并发送(Background running; For the running front desk program, the desktop program specifies the location capture, stitching, image recognition to obtain monitoring data, save and send)
2222e
- C*** THEY MUST BE CHANGES TO COMMENT CARDS BEFORE COMPILING IN C*** FORTRAN-IV.
epc_wall 2
- Extended Kalman Filter Lecture note 251
图像识别
- 基于微软的MODI,用于识别文字,识别率不高,用于初学者理解(Based on Microsoft's MODI, used to identify text, recognition rate is not high, for beginners to understand)
mnist.pkl代码原文
- BP算法的实现,其中的手势识别,用python语言,在tensorflow下!(Implementation of BP algorithm)
OCR识别验证码
- 识别验证码,方便了识别验证码,只是个人一点观点,提供下而已(Identification verification code)
keras-master
- 神经网络用来keras框架源码,非常的适合初学者来学习卷积神经网络(Keras neural network framework for source code)
Tess4J
- 处理文字识别,满足文字识别,但目前有些中文识别还不是那么的精准。(Processing text recognition, to meet the text recognition, but now some Chinese recognition is not so precise.)
ann数字识别
- 首先训练一组文字,然后进行识别,识别准确率较高,比较容易上手的代码(First, train a set of words and then identify them)
Character_Recognition
- 本程序主要参照论文,《基于OpenCV的脱机手写字符识别技术》实现了,对于手写阿拉伯数字的识别工作。识别工作分为三大步骤:预处理,特征提取,分类识别。预处理过程主要找到图像的ROI部分子图像并进行大小的归一化处理,特征提取将图像转化为特征向量,分类识别采用k-近邻分类方法进行分类处理,最后根据分类结果完成识别工作。 程序采用Microsoft Visual Studio 2010与OpenCV2.4.4在Windows 7-64位旗舰版系统下开发完成。并在Windows xp-32位系统下测试
digitize2
- 能够分辨图像中任何一个点的坐标,方便快捷,准确(this can distinguish the number value of the figure)
颜色识别
- 识别红绿蓝三种颜色,识别判断出三种颜色的质心,(Recognize the color and identify the center of mass)
