搜索资源列表
CorrectCarNoImageAndRegnize
- 一种车牌图像校正新方法 【摘要】因摄像机角度而造成的机动车牌图像倾斜会对其后继的字符分割与识别带来不利的影响。本文在分析了车牌倾斜模式的基础上,提出了一种基于最小二乘支持向量机(LS-SVM)的车牌图像倾斜校正新方法。通过LS-SVM线性回归算法求取坐标变换矩阵并对畸变图像进行旋转校正。主要方法:首先,将二值倾斜车牌图像中的像素转换为二维坐标样本,并构造图像数据集 再通过LS-SVM线性回归算法对该数据集进行回归,求取主要参数 最后,再由该参数转换为能反映图像倾斜方向的2维坐标变换矩阵。实验
PCA_Face_Recognition
- 特征脸识别算法的完全Matlab实现,内附有详细的训练集、测试集和使用说明-Eigenface algorithm to achieve the full Matlab, enclosing a detailed training set, test set and instructions for use
Metaface_ICIP
- 利用稀疏表示一集字典学习的方法进行人脸自动识别的Matlab算法,是经典SRC方法的提高-That a sparse set of dictionary use of learning methods in Matlab automatic face recognition algorithms, is the classic method of improving SRC
aco-v1.1
- 采用蚁群优化算法的轮廓匹配,输入可以是二值轮廓或者是任意的二维点集-This MATLAB implementation computes a correspondence between two shapes based on ant colony optimization (ACO). The input shapes can be either two 2D contours (open or closed) or two arbitrary sets of 2D points.
Kalman
- matlab上的卡尔曼滤波滤波算法合集,基本包含所有的卡尔曼滤波算法(Matlab on the Calman filter algorithm collection, basically contains all the Calman filter algorithm)
Character Recognition
- 有关于字符识别,运用了OCR算法,内含完整的数据库和训练程序,还有一些测试集(From the matlab file exchange center, the character recognition written by the foreign gods, using the OCR algorithm, contains a complete training database.)