HW3

关于图形学的一个算法，主要实现了投影。比较适合初学者(An algorithm on the graphics, the main achievement of the projector. More suitable for beginners)

程序可实现dwg文件注记的批量替换, 可根据需要进行扩展。(Dwg file program allows batch replacement Note)

摄像机标定程序，实现单目，双目摄像机的标定(calibration of camera )

图像经过双随机处理和分数阶傅里叶变换，可以达到加密解密的功能，且对密钥敏感性较强。(The image undergoes double random processing and fractional Fourier transform, which can achieve the function of encryption and decryption, and has strong sensitivity to the key.)

jpeglib的库文件，方便实现很多关于jpeg的操作，例如格式转换等等。(jpeglib the library file to facilitate the achievement of the operation of a number of jpeg, for example, format conversion and so on.)

此jar包用于解析jbig格式文件的工具包，调用接口即可(This jar package is a toolkit for parsing JBIG format files and calling interfaces.)

说明：  UNet最早发表在2015的MICCAI上，短短3年，引用量目前已经达到了4070，足以见得其影响力。而后成为大多做医疗影像语义分割任务的baseline，也启发了大量研究者去思考U型语义分割网络。而如今在自然影像理解方面，也有越来越多的语义分割和目标检测SOTA模型开始关注和使用U型结构，比如语义分割Discriminative Feature Network(DFN)(CVPR2018)，目标检测Feature Pyramid Networks for Object Detection(FPN)(CVPR 2017)等。(Its influence has reached 70% in 2015. Then it became the baseline that most of the medical image semantic segmentation tasks, and inspired a large number of researchers to think about the U-shaped semantic segmentation network. In the aspect of natural image understanding, more and more SOTA models of semantic segmentation and object detection begin to pay attention to and use U-shaped structure, such as semantic segmentation, discriminative feature network (DFN) (cvpr2018), feature pyramid networks for object detection (FPN) (CVPR 2017), etc.)

说明：  这个Matlab程序实现了二维图像到三维图像的纹理映射功能。作者原本，把它用于MRI医学图像中。(The Matlab program achieved a two-dimensional image into three-dimensional image texture mapping function. Author of the original, it used in MRI medical images.)

关于车辆跟踪的c++程序，使用了opencv进行跟踪，采用了帧差方法效果还不错(vehicle detection)

人工神经网络用于图像分割的matlab程序代码，此程序分割的是车牌图像(Artificial neural network for image segmentation matlab code, this procedure is the license plate image segmentation)