资源列表
caisetiqu
- 首先进行图像隐写,然后在提取秘密信息之前选择攻击模式,总共有个九个攻击模式,之后再提取出水印图像-Image steganography in the first, then choose attack mode before extracts secret information, a total nine attack patterns, and then extract the watermark image
ysxzpp
- 数字图像处理源代码,颜色图像匹配代码,主要计算颜色直方图-Digital image processing source code, color image matching code, mainly calculate the color histogram
jiaotongcanshujiance
- 涉及交通参数检测,包括虚拟线圈的设置,阴影消除和背景更新。-Traffic parameter detection, including virtual coil set, eliminating the shadow and background update.
zftjhh
- 直方图均衡化,直方图匹配,邻域平均,局域增强,中值滤波-Histogram equalization, histogram matching, neighborhood average, local enhancement, median filtering
hdtxcl
- 图像灰度变换,学会用Matlab软件对图像灰度进行变换;感受各种不同的灰度变换方法对最终图像效果的影响。-Gray transform, learn to use Matlab software to transform the image gray feel the impact of various different gray transform effect on the final image.
Watershed
- 分水岭算法,对图像进行超像素分割的函数,没有example,请自行调用-watershed image segmentation
to-detect--human-face-
- 检测并标识人脸的代码,可用于人脸检测,机器学习-To detect and identify the human face of code that can be used face detection, machine learning
camshif
- 运用高斯模型与camshift结合的方法实现全自动人员检测-Gaussian model using the method of combining with camshift achieve automatic detection staff
2D-linear-fitting
- 2D直线拟合,忽略了离群点,在测量值被高噪声,传感器故障等破坏的实际应用中十分重要-2D linear fitting, ignoring the outliers, are very important in high-noise measurements, sensor failures and other damage in the practical application
Pyramid-lucas-kanade-optical-flow-
- 金字塔lucas-kanade光流代码,可用于动态背景,但速度较慢-Pyramid lucas-kanade optical flow codes, can be used for dynamic background, but slower
picture-clipping
- 将图片随机剪裁成固定大小的图片,适用于机器学习中剪裁负样本-The image randomly cut to a fixed size image, for machine learning tailoring negative samples
hardexample
- 是指利用第一次训练的分类器在负样本原图上进行行人检测时所有检测到的矩形框,这些矩形框区域很明显都是误报,把这些误报的矩形框保存为图片,加入到初始的负样本集合中,重新进行SVM的训练,可显著减少误报。这种方法叫做自举法-The first is the use of trained classifier all detected rectangle detect pedestrians in the negative when the sample picture, the rectangular
