DLTs-L-approximation-code

说明：  目前一种快速稳健的卷积神经网络yolov3的代码，在protorch平台上运行(At present, the code of yolov3, a fast and robust convolutional neural network, runs on the platform of protorch)

说明：  其可以直接绘制vaspkit生成的能带图，直接调用即可，可以批量生成能带图(It can directly draw the band diagram generated by vaspkit)

精通MATLAB数字图像处理与识别 chapter11 代码(Proficient in MATLAB digital image processing and recognition chapter11 code)

说明：  这篇论文提出了一种较好的水下图像增强的方法。首先使用经过端到端训练的卷积神经网络去测量输入图片，同时以自适应双边滤波器对传输图片进行处理。接着提出一种基于白平衡的策略来消除图片的颜色偏差，用拉普拉斯金字塔融合获得无雾和色彩校正图像的融合结果。 最后，输出图像被转换为混合小波和方向滤波器组（HWD）域，用于去噪和边缘增强。 实验结果表明，该方法可以消除颜色失真，提高水下图像的清晰度。(This paper proposes a better underwater image enhancement method. Firstly, an end-to-end training convolutional neural network is used to measure the input image, and an adaptive bilateral filter is used to process the transmitted image. Then a strategy based on white balance is proposed to eliminate the color deviation of images. The fusion results of fog-free and color correction images are obtained by Laplacian pyramid fusion. Finally, the output image is converted into hybrid wavelet and directional filter bank (HWD) domain for denoising and edge enhancement. The experimental results show that the method can eliminate color distortion and improve the clarity of underwater images.)

应用opencv进行图像处理，改变基sobel算子操作，有利于开展下面的图像处理(Applying OpenCV to image processing and changing the operation of base Sobel operator is beneficial to the following image processing)

这是一个阈值分割算法，主要用来对图像进行二值化，提取感兴趣区域~~(This is a threshold segmentation algorithm, mainly used for binary images, extract region of interest ~ ~ )

产生正弦信号，加入高斯白噪声，并用小波方法去噪(Produce sine signals, add white gaussian noise, and wavelet denoising method )

多分类问题的支持向量机源程序一对一方法 绝对可以运行(Multi-class SVM using One-Against-One decompositionoao)

jpeg基本系统编解码实现程序，内附说明文件。(the programs of coding and encoding for then basic system of jpeg.PS:Readme.txt)

轮轨接触CONTACT程序，可以用来计算轮轨磨耗(Wheel-rail contact CONTACT procedures can be used to calculate the wheel-rail wear)