xiaobo53

说明：  该压缩包内含有基于梯度金字塔变换的多模态图像融合方法的MATLAB代码，可以直接运行，得到融合结果。另外，压缩包内包括了多组已配准、待融合的图像示例，具体包括红外图像与可见光图像、CT与MR图像，多聚焦图像。本人还对代码进行了必要的解释。推荐下载(The compression package contains matlab code of multimodal image fusion method based on gradient pyramid transformation, which can be run directly to get fusion results. In addition, the compressed package includes several groups of images that have been registered and to be fused, including infrared images and visible images, CT and MR images, and multi focus images. I also gave the necessary explanation to the code. Recommended download.)

基于稀疏表示的图像融合算法 KSVD OMP(Image fusion algorithm based on sparse representation KSVD OMP)

对清晰图像加模糊并用时域和频域的方法分别实现对模糊参数的估计并将图像复原（其中用频域的方法实现对模糊角度的估计）(Clear picture of the additive fuzzy and time-domain and frequency domain methods, respectively, to achieve the estimated fuzzy parameters and image restoration (including the method used to achieve frequency domain point of view of fuzzy estimates))

基于SURF算法实现图像特征提取与描述，使用RANSAC进行图像细配准(SURF algorithm was used to extract and describe image features, and RANSAC was used for image registration)

基于dft变换域的图像水印嵌入程序，通过修改分块dft系数实现水印嵌入，可实现，供初学者参考。(Dft transform domain image watermarking embedding the watermark embedding process by modifying the block dft coefficients, achievable, and reference for beginners.)

本程序实现了对指纹图像的预处理、特征提取，效果很好，有图有程序，可以直接使用。(This procedure to achieve the fingerprint image preprocessing, feature extraction, the effect is very good, there are plans to have procedures can be used directly.)

otsu算法实现，可以自适应获取阈值，对图像进行二值化。里面面配有图像均衡化的程序一起使用，效果更好， (otsu algorithm adaptive obtain the threshold image binarization. Inside surface with image equalization program used together, the better)

a lane dtection method using hough-transform

将原始载体图片经过一维冗余离散小波变换分成四个子频带，分别对每个子频带进行奇异值分解， 将水印图片灰度值直接按比例缩小嵌入到奇异值矩阵中，再将此矩阵进行一次奇异值分解得到奇异值当做此子带的奇异值， 重建此子带矩阵，而后将进行反冗余离散小波变换得到嵌入载体后的水印图像。(The original image after the one-dimensional vector redundant discrete wavelet transform is divided into four subbands, respectively, of each sub-band for the singular value decomposition, the watermark image gray value scale down directly embedded into the matrix singular value, then this matrix is ​ ​ a Singular value decomposition singular value as the singular values ​ ​ of this sub-band, the reconstruction of this sub-band matrix and after anti-redundant discrete wavelet transform watermark image after embedding the carrier.)

说明：  Kylberg Sintorn数据集可用于进行算法的旋转不变测试，然而官网中并没有直接划分训练集与测试集，本代码对该数据集的图片进行重新命名与划分，可用于算法测试中(The Kylberg Sintorn dataset can be used to perform the rotation-invariant test of the algorithm. However, the official website does not directly divide the training set and the test set. This code renames and divides the picture of the dataset, which can be used in algorithm testing)