资源列表
InTech-Object_tracking
- e book for object recognition
face
- 通过眼睛来匹配照片人像的相似度，可以查看下哇-Photo portrait by eye to match the similarity, you can view the next wow
CT_MATLAB_v0
- CT压缩跟踪算法，自带三个视频序列可供实验，跟踪效果不错-CT compression tracking algorithm, with three video sequences for experiment, the tracking effect is good
SupPlate
- 车牌识别系统软件的调用代码.单台计算机可实现卡口最多可支持2方向8车道,闯红灯最大可支持4方向16个车道，为纯视频触发方式，替代地感线圈等外部触发方式，为用户节约很大一部分的成本。本控件视频检测全天抓拍率大于95 ，车牌识别率超过98 ，识别准确率约90 -LPR SDK
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
HandWriteOCR
- 手写汉字识别程序，包含训练和检测两部分，基于mnist库做训练和测试(Handwritten Chinese character recognition program, including training and testing of two parts)
Pattern-Recognition-ppt
- 介绍模式识别的基本概念，详述了贝叶斯，参数估计，线性分类器，神经网络，随机方法，无监督学习与聚类等-Introduce the basic concepts of pattern recognition, Bayesian detailed, parameter estimation, linear classifiers, neural networks, stochastic methods, unsupervised learning and clustering, etc.
L1_tracker
- l1范数跟踪算法，很多详细注释，可以直接使用，论文得从新下载-The l1 norm tracking algorithms, a lot of detailed annotations, can be used directly, the papers the new download
96
- Face Recognition book for people that want to advance on computer vision
01_AES2410
- 指纹库，采集仪为AES2410，提供约500幅图像，生成库无背景和光学背景的各提供约5,000幅。指纹识别的有用-Fingerprint database, collection instrument for the AES2410, providing about 500 images, generated libraries and optical background, no background of about 5,000 pieces of each
VC2008_TrackEye_noerror
- 脸部识别与眼部识别 vc2008 环境下-Facial recognition and eye recognition under vc2008
dist
- 不用安装tesseract-ocr软件，直接可以调用方法识别图片文字(No need to install tesseract-ocr software, you can directly call the method to identify picture text)