f_threshold

自己用matlab写的灰度图像压缩解压程序 jpegencoder可以打开图像压缩后存储为c.jpg（只限于灰度图像） jpegdecoder只适用于把jpegencoder的c.jpg解压，还不可以对任意图像解压，有待以后完善 作者 ar_dong(jpegencoder jpegdecoder author ar_dong)

卡耐基梅隆大学AAM算法中标定人脸上68个标志点的matlab程序(locate the landmark in the face images)

说明：  自己写的fft的应用实例，包括对一维振动信号分析，对二维图像频谱分析。(The application examples of FFT written by myself include one-dimensional vibration signal analysis and two-dimensional image spectrum analysis.)

说明：  通过hough变换求图像中的圆的参数（圆心坐标和半径）(Through the hough transform for image circle parameters (center coordinates and radius))

把图像从RGB格式转换到YUV格式的一个函数，直接调用，管他有没有，上传了再说(Image conversion from RGB format to YUV format of a function, a direct call, though he did not upload to say)

压缩感知重构算法，在经典的SP基础上进行的改进，提高了性噪比，以DWT为稀疏基。(Compressed sensing reconstruction algorithm, improved on the basis of the classic SP carried out to improve the signal to noise ratio, DWT is sparse groups.)

matlab写的对图像进行简单的伽马校正，代码中给出了两个例子(matlab write simple image gamma correction, the code gives the two examples)

打开bmp位图文件 彩色转灰阶 直方图均衡 直方图规定 灰阶线性化(Open the bmp grayscale bitmap image binarization functions connected domain extraction features)

对输入的图像帧感兴趣区域进行逆透视投影变换，得到俯视图。(The input of the image frame of interest in the area of the inverse perspective projection transform, get a top view. InversePerspectiveMapping)

用DHNN （离散Hopfield网络）存储6幅图像作为联想记忆信息，然后对图像进行加噪处理，用所设计的DHNN进行图像复原，给出结果。(Storing DHNN (discrete Hopfield network) six images as associative memory information, and then add noise to the image processing, image restoration designed with DHNN, shows the results.)