tiffsilde

说明：  基于opencv的图像灰度化，将24位彩色图像重新量化为8位灰度图像(gray image)

这个算法包实现了从多幅拥有共同结构的图像里提取出共同形状的骨架。( This package implements the algorithm for Sketching the Common as described in: Shai Bagon, Or Brostovsky, Meirav Galun and Michal Irani "Detecting and Sketching the Common", CVPR 2010)

机器视觉之模糊图像复原，实现inverse Filter, Wiener Filter, Lucy-richardson 算法，里面包括PPT，代码和报告。非常有价值，值得参考！ (Machine vision blurred image restoration, achieve The inverse Filter, Wiener Filter, Lucy-richardson algorithm, which includes the PPT, the code and report. Very valuable and worth considering!)

说明：  利用相位一致性提取图像边缘，K-means聚类后区域生长进行图像分割，附参考论文。(Using phase coherence image edge extraction, K-means clustering image after region growing segmentation, attached reference paper.)

各类图形处理算法代码，齐全的图形处理算法，可以直接运行。去噪，识别，检测，拼接等(Complete graphics processing algorithm, you can run directly. Denoising, identification, detection, stitching and so on)

文字识别的结构特征提取子函数。对不同字型的字进行提取。(Character Recognition structural feature extraction Functions. Text of different characters extracted.)

用于单目标追踪的多模概率假设粒子滤波程序(MM-PHD for single target)

首先读入图像，转化成hsi彩色空间，然后只对亮度I分量作直方图均衡化，最后合成三个分量返回到RGB图，但是这种方法容易使颜色失真，失去了部分图像细节。(First read in the image, into the hsi color space, and then only on the brightness I component for histogram equalization, the final synthesis of the three components of return to RGB chart, but this method is easy to make color distortion, loss of part of image detail. )

一种基于DCT域盲数字水印嵌入程序，在DCT中频系数中嵌入水印，恢复時不用用到原始图像。(Based on DCT-domain blind digital watermark embedding process, in the intermediate frequency DCT coefficients to embed watermarks, when not used to restore the original image.)

1.本程序功能包含显示直方图，OTSU的单值分割，OTSU的二值分割,OTSU的三值分割 2.在OTSU的分割时，通常情况下我们是通过类间方差得到一个分割阈值，但是有时候我们需要得到各灰度级别的目标，那么采取多值分割是 很必要的，通过改进得到OTSU的多值分割方法 3.本程序另外还有显示直方图，计算程序运行时间，处理结果以新的窗口显示等细节，这部分适合MFC初学者。(1. This procedure shows the histogram feature, OTSU single segmentation, OTSU binary segmentation, OTSU three segmentation 2. OTSU segmentation, it is usually the case we are through the between-cluster variance by a partition threshold , but sometimes we need to be the gray level of the target, then the multi-segmentation is necessary, through improved access to multi-OTSU segmentation methods 3. This procedure in addition to show the histogram to calculate run time, treatment the results of a new window display the details of this part of MFC for beginners.)