127

说明：  一个改进的自适应canny算法，该方法采用改进的开关型中值滤波器对图像做去噪工作，再把整幅图像分割为若干子图像，最后在充分考虑全局以及各子图像的边缘梯度信息后，自适应地生成动态阈值。(The new Canny adaptive method divides image into sub-images,then determinates the thresholds automatically according to the whole image edge information and the sub-images edge information.)

经典的ukf跟踪框架与源码，有详细的注释以及说明，适合初学者。(Classic ukf tracking framework and source code, detailed notes and instructions for beginners.)

SPIHT的图像压缩算法源代码。可以针对128×128的图像进行压缩(SPIHT image compression algorithm source code. 128 × 128 image compression)

实现两幅图像匹配。应用SSD+SAD+NCC算法的匹配，很好用的程序(Realizing Two Image Matching.Application of SSD+SAD+NCC algorithm matching, very useful program)

目标检测，利用上下文关系 (object detection using context)

Godec底秩矩阵去噪算法，包含论文和代码(Godec denoising bottom rank of the matrix, containing papers and codes)

对指纹进行识别，通过gabor进行指纹增强，然后细化得到结果(Fingerprints were identified and enhanced with gabor, and the results were refined)

线性同余伪随机数发生器、小数开方伪随机数发生器、利用Logistic方程和混合光学双稳模型产生混沌序列产生的序列矩阵(Linear congruence pseudo-random number generator, decimal square pseudo-random number generator, using Logistic equation and hybrid optical bistable model to generate sequence matrix generated by chaotic sequence)

说明：  利用全卷积神经网络，实现图像的语义分割，基于tensorflow的keras可以直接运行(Using the full convolutional neural network to achieve semantic segmentation of images, keras based on tensorflow can be run directly)

基于马尔可夫随机场的图像恢复，给出产生MRF的程序并应用于图像去噪(GMRF based on the image restoration, MRF is generated and applied to the procedures Image Denoising)