资源列表
FANFBP_ED_v2
- 等距扇形束CT重建的经典FBP算法，参考《医学成像系统》完成。-Isometric fan-beam CT reconstruction of the classic FBP algorithm, refer to " medical imaging system" to complete.
Polygonising-a-scalar-field
- 次算法是描述数据可视化等值面提取的核心代码，用到的是移动立方体的查找表算法，思路是查找表，具体信息将在文档中描述-Polygonising a scalar field
calibration
- 上传程序为利用vc编写的近景摄影测量程序，包括影像匹配，基本矩阵生成，核显影像生成等等。-Upload the program for the use of close-range photogrammetry vc written procedures, including image matching, basic matrix generation, nuclear generation, and so was the image.
Wdeconvolution-
- 维纳滤波和盲去卷积算法，解释如何实现对图像的后期处理和增强，步骤详细-Wiener filtering and blind deconvolution algorithm, explain how to achieve the image of the post processing and enhancement, step by step
denoisingmatlab
- 常用的图像去噪算法，基于隐马尔可夫树模型的小波去噪 基于尺度空间和context模型相结合的自适应小波去噪 基于尺度和空间混合模型的小波图像去噪 Bayes估计阈值软门限去噪 -The denoising algorithm used in image denoising, wavelet hidden Markov tree model based on adaptive wavelet denoising combining the scale space and context mode
sfr3
- 清晰度计算完整代码，针对SFR MTF的计算，包括镜头畸变的矫正，平滑等功能-Definition computing complete code, SFR MTF calculations for, including the lens distortion correction, smoothing function
cnn
- 用于图像分类的源代码，深度学习的应用，cnn卷积神经网络的使用，可以自己更换数据集或者调优，适合初学者使用！-For image classification of the source code, the application of in-depth learning, cnn convolutional neural network, you can replace the data set or tuning, suitable for beginners!
Untitled
- 基于三帧差分法的运动目标识别，简单有效，更换视频名即可直接运行。-Three difference method of moving target recognition, simple and effective, replace the name of the video can be run directly. Based
HOG-descriptor-master
- 提取图像的HOG(梯度方向直方图)特征描述符-abstract the HOG feature of images
iradonclj
- 平行光CT重建，频域滤波反投影iradon代码-FBP iradon
NPDFaceDetector
- NPD人脸检测主要内容： 1.图像特征：Normalized Pixel Difference(NPD)，存在查找表中。 2.特征筛选：deep quadratic tree 3.分类：soft cascade classifier-NPD Face Detection Content: 1. Image features: Normalized Pixel Difference (NPD), the presence of a lookup table. 2. Filter
Image-stitching-Based-on-SURF
- 该程序采用快速鲁棒特征点的图像拼接技术，该算法具有鲁棒性好，对图像序列中的光照变化、尺度变化、旋转变化具有良好的适应性。-The program uses fast image stitching robust feature points that the algorithm has better robustness and image sequence lighting changes, scale changes, changes in the rotation has a good a