资源列表
Actual+JPEG
- 一个在MATLAB的JPEG例程，包括编码器和解码器(an example to encode jpeg format picture in MATLAB)
stacking
- kaggle digitrecognizer MNIST by stacking some machine learning method, such like GBM(Gradient Boosting Method), LR, Extra Randomized Trees, Random Forest,KNN,etc.用stacking的方法实现手写数字识别MNIST。(kaggle digitrecognizer MNIST by stacking some machine learnin
Halcon12_x86_x64
- halcon12 永久dll，可以不使用license，亲测可用(Halcon12 permanent DLL, which can be pro tested without license)
caffe-tensorflow-master
- 实现CamVid数据集分割功能，利用caffe转tensorflow模型，得以实现，使用FCN网络(come true the function of datasets of CamVid to segmantic segmentation)
gait-recognition-master
- I利用了深度学习，实现视频中的人的步态行为检测。(In this project you can find implementation of deep neural network for people identification from video by the characteristic of their gait. The processing is very robust against various covariate factors such as clothing, ca
61737015coherencefilter
- 图形图像处理中的图像去噪算法研究，希望可以帮到您。(The research of image denoising algorithm in graphic image processing, hope to help you.)
车牌
- 基于matlab的车牌检测程序。。。。。。(License plate detection based on MATLAB)
图像质量评价
- 融合图像质量评价，包括标准差，平均梯度，信息熵等(Fusion image quality evaluation, including standard deviation, average gradient, information entropy and so on)
fft
- 主要是FFT计算傅里叶变换的幅频特性函数文件(The main is the amplitude frequency characteristic function file of FFT calculation Fourier transform)
python_feature_signalgorithm
- 用Python通过L1-penalized minimization problem实现人脸识别算法(Solve an L1-penalized minimization problem with the feature sign search algorithm of Lee et al (2006).)
OTSU
- 图像阈值分割的C++实现，能够自动计算图像阈值，没有图片大小的限制。并且封装位子函数类型，可直接调用。测试性能优秀。(Automatically calculate the image threshold on the C++ platform, and there is no limit of the size of the image. And encapsulate the type of the bit function, which can be called directly. Th
Circle
- 实际检测环境无法采集到完美的圆，所以Hough变换检测圆心经常存在偏差。该程序可检测不同角度，不同畸变圆的圆心，并输出其圆心坐标。利用C++实现。(The actual detection environment can not collect the perfect circle, so the Hough transform is often biased to detect the center of the circles. The program can detect the cent