image-fusion

使用cnn + svm的分类，结果运行不错(Using CNN + SVM classification, the result runs pretty well.)

Image Indexing Using Color Correlogram

说明：  全变分去噪程序，用于图像去噪，该方法能克服图像去噪中的震荡效应，使图像更加光滑，并能保存边缘信息。(total variation denoisy)

改进陈显毅GUI程序,可实现对异模情况下的配准，对边缘较明显的图片用处很大(The improvement of the Chen GUI program)

图像匹配，可以实现目标图像的匹配，匹配出最相似的训练图片。(Image matching, the matching can achieve the target image, matching the most similar training images.)

从眼动仪提取数据，根据高斯核函数得到感兴趣区域(Extract data from the eye tracker, based on the Gaussian kernel function to get the area of ​ ​ interest)

lejos ev3 project the control interface and move

说明：  基于Robert算子、Sobel算子、Prewitt算子、Log算子、Canny算子的边缘检测代码(Edge detection code based on Robert operator, Sobel operator, Prewitt operator, LOG operator and Canny operator)

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.)

阵列信号处理方面的经典程序，包括MUSIC算法，ESPRIT 算法，Root-MUSIC算法面阵中二维角度估计 Unitary -ESPRIT算法，空间平滑MUSIC算法，传播算子DOA估计算法等等(Classical array signal processing procedures, including the MUSIC algorithm, ESPRIT algorithm, Root-MUSIC algorithm for two-dimensional planar array of point estimates Unitary-ESPRIT algorithm, spatial smoothing MUSIC algorithm, propagator DOA estimation algorithm, etc.)