wavepack-change

显示图像灰度，可以鼠标点击显示的起始位置及设置显示区域的大小(show the gray of picture ,can click the position and set the scales)

根据指定字符分割字符串，VC++精选编程源码，很好的参考。(According to the specified character segmentation character string, VC++ select programming source code, a good reference.)

h264实现监控,不是动态的，是通过读取每一帧图像(h264 yuv420 to rgb)

传统的图像分割方法可以分为基于阈值、边缘、区域的方法等，而传统的分割方法在复杂图像分割中效果不好。为了提高图像分割的性能，我们提出了一种基于局部自适应窗口的Otsu方法。首先，分析了传统阈值法在复杂图像分割中不能很好地形成的原因，比较了全局阈值和局部阈值对图像分割的影响。其次，提出了根据局部信息自适应地改变局部窗口大小的方法，分析了该方法的特点。最后，证明了所提出的新方法优于其他方法。实验结果表明，与其他传统方法相比，该方法能保持更多的细节，获得更满意的结果。(The traditional image segmentation methods can be divided into thresholding, edge and region methods. The traditional segmentation methods do not perform well in the segmentation of complicated images. In order to improve the performance of image segmentation, we propose an adaptive windowed range-constrained Otsu method based on local information.First, the reason why traditional thresholding methods do not perform well in the segmentation of complicated images is analyzed. Therein, the influences of global and local thresholdings on the image segmentation are compared. Secondly, a method of adaptively changing the local window size based on local information is proposed, and the characteristics of the proposed method are analyzed. Finally, the superiority of the proposed method over other methods, It is validated by the experiments that the proposed method can keep more details and acquire much more satisfying results as compared with the other conventional methods.)

说明：  通过纹理方向估计消失点，通过消失点来检测道路区域。 该程序应用到了基于纹理的张量投票算法来估计消失点；通过纹理方向和颜色信息，生成用于估计两个最主要道路边界的直方图；最后将道路区域定义为两个检测到的道路边界之间且低于估计的消失点的区域(The vanishing point is estimated by the texture direction, and the road area is detected by the vanishing point. The program applies a texture-based tensor voting algorithm to estimate the vanishing point; through the texture direction and color information, generates a histogram for estimating the two most important road boundaries; finally defines the road area as two detected road boundaries. An area between and below the estimated vanishing point)

说明：  基于双边滤波的retinex算法，暗光图像增强，有效去噪、提高对比度、去光晕；含论文和讲解PPT、实例代码(Retinex algorithm based on bilateral filtering can enhance dark image, effectively denoise, improve contrast and eliminate halo)

图像检索——提取颜色特征：HSV空间颜色直方图(将RGB空间转化为HSV空间并进行非等间隔量化，将三个颜色分量表示成一维矢量，再计算其直方图作为颜色特征。(Image Retrieval- extract color features: HSV space color histogram (RGB space into the HSV space and the non-interval to quantify the three color components expressed as a one-dimensional vector, then calculate the color histogram as a feature.)

说明：  利用ikmeans算法实现图像分割matlab代码(ikmeans algorithm to deal image segmentation)

将原图像进行退化处理（选择大气湍流导致图像模糊时相应的PSF），然后将退化后的图像进行复原（使用维纳滤波、直接逆滤波）.(The original image degradation process,and then restore the degraded image with Wiener filtering and inverse filtering.)

多样性密度算法,EM-DD算法,最好的多示例学习算法之一,MATLAB实现.(Diverse density algorithm, EM-DD algorithm, one of the best multi-instance learning algorithm, MATLAB.)