JPDA

实现运动模糊图像的非盲卷积 分区域去模糊 有用(Implementation of motion blurred image blind deconvolution is useful to fuzzy areas)

对图像做spca有监督的主成分分析降维，并投影回图像来降噪，在本程序中，使用正弦函数控制图像变化，函数值作为监督信息(Image do spca supervised principal component analysis dimension reduction, noise reduction and projected back images)

说明：  二值化程序：实现自适应二值化。效果较好，二值化后图片较清晰(Binarization process: the realization of adaptive binarization. Better, after binarization clearer picture)

利用基于直方图的自适应阈值方法实现分割前景与背景(The use of foreground and background to achieve segmentation adaptive threshold method based on histogram)

解决散斑图像的重建问题,主要是使用了相位恢复算法(to study the picture problem)

说明：  Forstner算子提取特征点 Forstner算子 提取特征点 (Forstner operator extracting feature points Forstner operator extracting feature points)

说明：  PCA图像降噪新算法-LPG PCA，全名叫做Two-stage Image Denoising by Principal Component Analysis with Local Pixel Grouping。内含算法代码和数据集，均经本人实测，可进行灰度图像和RGB图像的降噪，且PSNR和SSIM指标明显好于小波滤波、K-SVD等经典算法。值得学习图像降噪的看看！(The new algorithm of PCA image denoising LPG PCA, full name is two stage image denoising by principal component analysis with local pixel grouping. The algorithm code and data set can be used to reduce the noise of gray image and RGB image, and the PSNR and SSIM are better than the classical algorithms such as wavelet filtering and K-SVD. It's worth learning about image denoising!)

粒子滤波器（particle filter）程序，用粒子滤波器跟踪运动物体。(Particle filter (particle filter) process, with particle filter to track moving objects.)

pca 特征提取的源代码，对人脸识别很有帮助，(pca feature extraction of the source code, useful for face recognition,)

针对 Anrlod 变换的周期依赖于图像的阶数这一特性, 提出了一种反变换算法 。 该算法 通过分析加密图像任一点处两坐标分量间关系, 得到原图像相应点的坐标 , 从而实现图像的解密。(In view of the characteristic that the Anrlod transform cycle depends on the order of the image, an inverse transformation algorithm is proposed. The algorithm obtains the coordinates of the corresponding points of the original image by analyzing the relationship between the two coordinate components at any point of the encrypted image, so as to achieve the decryption of the image.)