SMD（灰度方差）

理论

当完全聚焦时，图像最清晰，图像中的高频分量也最多，故可将灰度变化作为聚焦评价的依据，灰度方差法的公式如下：

https://blog.csdn.net/Real_Myth/article/details/50827940

代码

def SMD(img):
    '''
    :param img:narray 二维灰度图像
    :return: float 图像约清晰越大
    '''
    shape = np.shape(img)
    out = 0
    for x in range(0, shape[0]-1):
        for y in range(1, shape[1]):
            out+=math.fabs(int(img[x,y])-int(img[x,y-1]))
            out+=math.fabs(int(img[x,y]-int(img[x+1,y])))
    return out

https://blog.csdn.net/Greepex/article/details/90183018

4. SMD（灰度方差）函数

当完全聚焦时，图像最清晰，图像中的高频分量也最多，故可将灰度变化作为聚焦评价的依据，灰度方差法的公式如下：

代码:

def SMD(img):
       # 图像的预处理
       reImg = cv2.resize(img, (800, 900), interpolation=cv2.INTER_CUBIC)  
       img2gray = cv2.cvtColor(reImg, cv2.COLOR_BGR2GRAY)  # 将图片压缩为单通道的灰度图
       f=self._imageToMatrix(img2gray)/255.0
       x, y = f.shape
       D = 0
       for i in range(x - 1):
           for j in range(y - 1):
               D += np.abs(f[i+1,j]-f[i,j])+np.abs(f[i,j]-f[i+1,j])
       return D

https://gist.github.com/JuneoXIE/d595028586eec752f4352444fc062c44

def _SMDDetection(self, imgName):
    # step 1 图像的预处理
    img2gray, reImg = self.preImgOps(imgName)
    f=self._imageToMatrix(img2gray)/255.0
    x, y = f.shape
    score = 0
    for i in range(x - 1):
        for j in range(y - 1):
            score += np.abs(f[i+1,j]-f[i,j])+np.abs(f[i,j]-f[i+1,j])
    # strp3: 绘制图片并保存  不应该写在这里  抽象出来   这是共有的部分
    score=score/100
    newImg = self._drawImgFonts(reImg, str(score))
    newDir = self.strDir + "/_SMDDetection_/"
    if not os.path.exists(newDir):
        os.makedirs(newDir)
    newPath = newDir + imgName
    cv2.imwrite(newPath, newImg)  # 保存图片
    cv2.imshow(imgName, newImg)
    cv2.waitKey(0)
    return score

https://github.com/Leezhen2014/python—/blob/master/BlurDetection.py