bianyuanjianceyufenge

Calculate the Laplacian of an image, can be accelerated by the GPU.

基于除法模型的鱼眼图像校正代码，包含摄像机内参和畸变参数在内的5个参数，无需进行填补空洞的操作。(Based fisheye image correction code division model, including internal camera and distortion parameters, including five parameters, without the need for filling voids operation.)

索书号文字图像分割，粘连字符切分，彩色车牌分割 ，文字识别的结构特征提取子函数(Call text image segmentation, character segmentation, color plate segmentation, text recognition feature extraction Functions)

说明：  通过选取初始种子点，进行图像的阈值分割，通过对比计算该点8领域灰度值是否符合阈值条件来对图像边缘进行分割(The image edge is segmented by choosing the initial seed point and comparing the gray value of the 8 domains of the point with the threshold condition.)

在视频文字检测以及提取方面，比较好的参考论文，大家可以下载参考！(Video text detection and extraction, a good reference papers, everyone can download the reference!)

改进的OPTA，通过设置保留模板，图形细化算法，matlab(Improved OPTA, retained by setting the template graphics thinning algorithm, matlab)

一种简单高效地基于压缩感知的跟踪算法。首先利用符合压缩感知RIP条件的随机感知矩对多尺度图像特征进行降维，然后在降维后的特征上采用简单的朴素贝叶斯分类器进行分类。该跟踪算法非常简单，但是实验结果很鲁棒，速度大概能到达40帧/秒(A simple and efficient tracking algorithm based on compressed sensing. Firstly, with the random sensing matrix compressed sensing RIP conditions for multi-scale image feature dimension reduction, and then use the naive Bias classifier simple classification in the feature reduction after the. The tracking algorithm is very simple, but the results are robust, speed can reach 40 frames per second)

合成孔径雷达（SAR）成像的距离徙动校正(Synthetic aperture radar (SAR) imaging distance migration correction)

基于分片重排列技术的维数约简方法，用于特征提取。(Patch Alignment for Dimensionality Reduction，IEEETrans.，2009.)

多聚焦图像融合的源代码，还包括几个评价指标的的function函数(Multi-focus image fusion source code, also includes several evaluation function function)