mingw

c 实现 canny算子(c realize canny )

基于灰度图像进行傅立叶变换后的二值化处理(Binarization based on the Fourier transform after the gray image processing)

若干次压缩后图像信噪比的变化情况，有子程序实现 (Several compressed image signal to noise ratio of the changes have Subroutine realize)

基于MeanShift算法将图像进行平滑处理去噪并分割(MeanShift algorithm based on smoothing the image de-noising and segmentation)

程序先用fspecial函数产生运动模糊图像，再用维纳滤波进行恢复(Procedures first fspecial functions to generate motion-blurred image, and then carry out the restoration of Wiener filtering)

图像检测的算法，Faster R-CNN算法，先对整张图像进行卷积计算，然后通过感兴趣区域池化层(RoI Pooling Layer)将选择性搜索算法推荐出来的候选区域和卷积网络计算出的特征映射图进行融合，得到候选区域对应的特征矢量，这种共享卷积计算的操作极大地减少了卷积计算的次数。而且这些特征矢量的维度统一，方便后续的分类工作。通过感兴趣区域池化层处理卷积特征，并将得到的特征送往两个并行计算任务进行训练，分类和定位回归。通过这些方法和改进的框架，Fast R-CNN 用更短的训练和测试时长，取得了比 R-CNN 更好的效果(Faster R-CNN algorithm first convolutes the whole image, then fuses the candidate regions recommended by the selective search algorithm and the feature mapping maps calculated by the convolution network through the RoI Pooling Layer to get the corresponding feature vectors of the candidate regions, which greatly reduces the number of convolution calculations. Moreover, the dimension of these feature vectors is unified, which facilitates the subsequent classification work. The convolution feature is processed by the pooling layer of the region of interest, and the obtained feature is sent to two parallel computing tasks for training, classification and positioning regression. Through these methods and improved framework, Fast R-CNN uses shorter training and testing time and achieves better results than R-CNN.)

Aptina ASX340图像传感器设计线路图及datasheet(Aptina ASX340 image sensor design schematics and datasheet)

图像融合拼接GUI设计，包括图像融合和图像拼接的matlab实现。(Image fusion splicing GUI design, including image fusion and image stitching matlab implementation.)

实现单尺度retinex算法，用于图像的对比度增强，对低能见度图像处理效果较好。(Retinex single-scale algorithm for image contrast enhancement, image processing on low visibility is better.)

提取图像的zernike特征参数，这个程序较难，关键这个是带程序说明的，让你一目了然(Extract images zernike characteristic parameters, this procedure is more difficult, the key to this is with a description of the procedures, at a glance)