matlabforlicenceplaterecognition

FSIM图像质量评价性能指标算法，衡量图像质量好坏程度(FSIM image quality uation performance index algorithm, to measure the degree of image quality )

利用PCL库，基于深度图像，进行点云特征提取(Based on the depth image, feature extraction of point cloud)

利用非参数贝叶斯字典学习模型进行图像稀疏表示(use non-parametric-bayesian-dictionary-learning-for-sparse-image-representations)

说明：  李春明提出的无需水平集初始化的思想是图像分割的一个重大突破，重庆大学的何传江教授对该算法进行了改进，里面是我的实现算法(Li Chunming s no need to initialize the idea of ​ ​ the level set image segmentation is a major breakthrough, Chongqing University, Professor He Chuanjiang to improve the algorithm, which is my algorithm )

FLICM一种基于模糊局部信息C均值聚类方法，是对传统FCM聚类方法的最近改进方法，具有更强的鲁棒性，效果明显优于传统算法。(A novel and robust FCM framework for image clustering called Fuzzy Local Information C-means (FLICM) clustering algorithm.)

通过数字图像相关的方法计算两幅图像之间的位移，计算时间较长，是最基础的DIC，没有优化。(Digital image correlation method to calculate the displacement between the two images, the time is longer, is the most basic DIC, no optimization.)

上下文意识的显著性检测，包含matlab代码和对应的CVPR2010论文。(It contains the paper Context-Aware Saliency Detection from CVPR2010 and it s matlab code. )

本文主要介绍遗传算法的基本理论，叙述遗传算法在图像增强的的主要应用，即将原始图像变得更加清晰，特征变得更加明显。 现今关于图像增强的算法有很多，而这些算法大多是基于退化函数或者点扩展函数的知识进行图像处理的。当图像出现模糊或噪声影响大时，设计出的图像清晰化的效果肯定不够理想，因此有必要对图像进行增强处理。于是，可利用到遗传算法这种成熟稳定的仿生物进化的全局寻优算法，进行图像增强，由于遗传算法控制参数少、自适应度高，将选择该方法对图像退化分别进行不同的清晰化处理. 这样既增强了图像的对比度,又克服了传统直方图均衡化处理所造成的灰度级损失等缺点。 通过实验去表明，遗传算法从全局寻优的角度出发，能够较为精确地估计退化系统函数。和传统的线性增强、直方图均衡进行比较。实验结果表明该方法能改善原图像视觉效果，便于之后的图像分析。 (This paper mainly introduces the basic theory of genetic algorithm, genetic algorithm (ga) in the main application of image enhancement, the original image is more clear, characteristic becomes more obvious. Today about the image enhancement algorithm are many, and most of these algorithms is based on the degradation function or the knowledge of the point spread function of image processing. When the image appears fuzzy or noise influence, designed the image clarity of effect must not ideal, therefore it is necessary to enhance the image. Then, genetic algorithm is available to the mature and stable evolution of the global optimization algorithm, for image enhancement, due to less genetic algorithm control parameters, since the high fitness, will choose the method of image degradation, respectively, to manipulate the different motivation. It can enhance the image contrast, and overcome the traditional histogram equalization processing grayscale loss caused by the faults. Throug)

Image processing and analysis

支持向量机的工具箱，对于图像处理中的分类识别学习者有着很大帮助。分享快乐！(SVM toolbox for image processing in the classification and identification of learners have a great help to me. To share their happiness!)