3.30-4.3-bianyuan

基于Maltab的gui图像配准程序。输入图像需为灰度图像。(matlab-based image registration)

双边滤波，在平滑噪声图像的同时又可保留图像的边缘信息(Bilateral filtering, the noise in the image while smoothing the image edge information can be retained)

为GABOR小波的详细MATLAB实现代码，详细分析了该小波的各种性能()

说明：  非下采样contourlet变换是一种较新的多尺度几何分析方法，能够很好地描述信号的线奇异特征，具有多方向滤波器组。(Nonsubsampled contourlet transform is a relatively new method of multiscale geometric analysis, can well describe the signal characteristics of the line singularity, with multi-directional filter.)

将RGB格式图像转换到YUV空间，输入RGB图像返回YUV格式数据(Converting RGB format images to YUV space)

Continuous Birdsong Recognition Using Gaussian Mixture Modeling of Image Shape Features

Zhang等人 利用相位一致性信息的特性，提出了 特征相似性方法(FSIMG) ，选取了相位一致性信息和梯度信息 作为它的两个特征，得到了较好的结果。 (A novel feature similarity (FSIM) index for full reference IQA is proposed based on the fact that human visual system (HVS) understands an image mainly according to its low-level features. Specifically, the phase congruency (PC), which is a dimensionless measure of the significance of a local structure, is used as the primary feature in FSIM. Considering that PC is contrast invariant while the contrast information does affect HVS’ perception of image quality, the image gradient magnitude (GM) is employed as the secondary feature in FSIM. PC and GM play complementary roles in characterizing the image local quality. After obtaining the local quality map, we use PC again as a weighting function to derive a single quality score. Extensive experiments performed on six benchmark IQA s demonstrate that FSIM can achieve much higher consistency with the subjective uations than state-of-the-art IQA metrics.)

去噪算法matlab源码三合一，包含BLS-GSM，BM3D，NLM(Denosing algorithms 3 in 1, include BLS-GSM+ BM3D+ NLM)

利用全卷积神经网络，实现图像的语义分割，基于tensorflow的keras可以直接运行(Using the full convolutional neural network to achieve semantic segmentation of images, keras based on tensorflow can be run directly)

对二维码图像进行灰度化、中值滤波、二值化、边缘检测、霍夫变换等预处理(The two-dimensional code image is grayscale, median filter, two valued, edge detection, Hough transform and other pre-processing.)