资源列表
CBIR
- 基于内容的图片搜索，通过图片的内容寻找相似的图片-Image searching based on the content
MachineLearningChapter4Face-recognizationSample.ra
- Tom M.Mitchell(CMU) 机器学习 第四章人脸识别例子源代码！有需要的可以下来研究一下！ 经典的东西总是很耐人寻味的！
decode_mnist
- 非常简短的mnist文件解析程序,两个函数分别解析image和label两种文件,返回为numpy的array类型,供opencv进一步处理及显示(A very short MNIST file parser. The two functions parse two files of image and label respectively, and return to the array type of numpy for OpenCV to further process and displ
keras_mnist_test
- hello Word of keras ,第一个成功实现的卷积神经网络,下载了mnist数据集,并decode,,然后,为了加快速度,训练其中的一部分数据,并用predict测试,ok,2min内出结果.(网上其它程序试过,训练太久,一晚上都没训练出结果,于是自己动手设计了这个小程序) 环境:python3.6,keras2.1,PC i5(很破的电脑)(Hello Word of keras, the first successful convolution neural network,
数字识别系统源代码
- 图像识别源码，vc6.0,可以移植到VS,值得学习,用的是自己的类(The source of image recognition is worth learning)
irisrecognition
- iris recognition contain a file to create iris template
ColAR_ALL
- AR 引擎 实现图片识别 效率优化 体积小，采用C++(AR engine for image recognition)
color-histogram-matching
- 本代码实现多视频下的目标识别的方法。使用了颜色直方图特征，并计算巴氏距离得出目标是否匹配。可以使用背景较为简单的视频进行实现。-The code to achieve the target recognition method of multiple video. Color histogram, and calculates the the Pap distance derived target match. Can use relatively simple background video
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)
sift-matlab
- 尺度不变特征转换算法（sift）在空间尺度中寻找极值点，具有位置、尺度、旋转不变性，可正常运行-Scale Invariant Feature Transform algorithm (sift) looking at the spatial scale of the extreme points, with the position, scale and rotation invariance, the normal operation
ANN
- OpenCV的ANN神经网络实现图像数字识别，可运行，能够达到99.9的准确率-ANN OpenCV neural network to achieve digital image recognition, can run, to achieve the accuracy rate of 99.9
VCPP
- 《图像模式识别—VC++技术实现》这本书的源码，对VC++编程非常有用-Image pattern recognition-VC technology to achieve "the source code of this book， it is very useful for VC programming.