pinpufenxi

Object Detection Combining Recognition and Segmentation, Eighth Asian Conference on Computer Vision (ACCV), 2007 源代码(Object Detection Combining Recognition and Segmentation, Eighth Asian Conference on Computer Vision (ACCV), 2007 source code)

针对多聚焦图像融合，本文首先介绍了小波变换融合算法，虽然小波变换方法无冗余，高频分量损失较小，具有较好的融合效果，但存在两个主要缺点：一是移变性，二是融合图像在重构时会受到一些外来因素的影响，所以仍会丢失一些边缘信息，为了克服小波变换法的以上缺点，可以采用基于小波分解和点扩展函数模型PSF相结合的融合方法。该方法首先对不同的图像进行无降2采样的小波分解，以保持与源图像大小相同，然后分别将其各方向、各尺度的高频分量进行叠加，并依此提取其高频分量的特征信息来判定清晰目标或模糊目标，以此来设计融合算法，采用一定的策略将两副源图像进行融合，从而避开了小波的反变换，因此融合后的图像具有比小波变换法更好的融合效果。(multi-focus image fusion, this paper introduces the wavelet transform algorithm, Although the wavelet transform non-redundant, the loss of high-frequency components are smaller, better integration effect, But there are two major drawbacks : First, the shift variability and the second is the integration of image reconstruction will be subject to a number of external factors. Therefore, there would still be some marginal loss of information, in order to overcome the wavelet transform of the above shortcomings, can be used based on wavelet decomposition and the point spread function PSF model combining the fusion method. The first pair of different images ratchet two sampling wavelet decomposition, and to maintain the same source image size. Then all of its direction, the scale of high-freque)

本文提出了基于二维混沌映射的数字图像水印算法，混沌具有随机性、似噪声及对初始条件的极端敏感性等特点。将经过二维混沌映射置乱后的数字水印信号嵌入图像小波域的低频系数，实现了数字水印的隐蔽性、保密性和稳固性；利用二维混沌映射Arnold变换对水印信号进行置乱，不仅增强了水印信号保密性，同时有效提高了视觉上抵抗图像剪切攻击的能力。(In this paper, two-dimensional chaotic map based on digital image watermarking algorithm, Chaos with random noise and the likelihood of extreme sensitivity to initial conditions and so on. Two-dimensional chaotic map will be scrambling after the digital watermark embedded image signal of the low-frequency coefficients in wavelet domain, the realization of a digital watermark hidden, security and stability the use of two-dimensional chaotic map on Arnold transform scrambling watermark signal, not only enhances the confidentiality of the watermark signal at the same time improve the visual image shear resistance attacks.)

Visual Tracking via Locality Sensitive Histograms.基于局部敏感直方图的目标跟踪算法，该算法在CVPR2013中出现，算法较简单但却非常有效，值得各位研究视觉跟踪算法的同行研究(Visual Tracking via Locality Sensitive Histograms)

PS处理过程中，利用迭代算法估计相干系数，并选取稳定点目标的算法实现。(PS process, using an iterative algorithm to estimate the coherence and stable point target algorithm)

本书详细介绍了医学图像注册方面的知识，包括配准的原理、刚性配准、非刚性配准，对于医学图像处理方面的研究具有很重要的参考价值。(The book details the registration of medical image information, including the principle of registration, rigid registration, non-rigid registration for medical image processing research has important reference value.)

这里包含了曲线波变换用于图像去噪的一片论文以及翻译，这是本人亲自翻译排版的，希望对大家有用(This includes the curvelet transform for image denoising is a piece of paper and translation, this is a personally Translation Publishing, I hope useful for everyone)

图像去雾 暗原色 导向滤波 最好的去雾算法 何恺明的matlab代码的opencv的实现(haze removal guided image filtering the best algorithm to fog )

说明：  包括pca和lda两个文件，先用pca降维后进行lda进行分类，用于人脸识别，实验结果很好。(It includes 2 files pca and lda. After the dimensionality reduction of pca, use lda for classification in face recognition. It has a very good experimental results.)

说明：  利用matlab实现不同曝光成度的图像融合，matlab实现HDR功能(Using matlab to realize image fusion with different exposure degrees, and using MATLAB to realize HDR function)