理论

Brenner梯度函数是最简单的梯度评价函数，它只是简单的计算相邻两个像素灰度差的平方，该函数定义如下：
Brenner 梯度函数 - 图1
其中：Brenner 梯度函数 - 图2 表示图像f对应像素点Brenner 梯度函数 - 图3的灰度值，Brenner 梯度函数 - 图4为图像清晰度计算结果。
https://blog.csdn.net/Real_Myth/article/details/50827940

算法

  1. def brenner(img):
  2.     '''
  3.     :param img:narray 二维灰度图像
  4.     :return: float 图像约清晰越大
  5.     '''
  6.     shape = np.shape(img)
  7.     out = 0
  8.     for x in range(0, shape[0]-2):
  9.         for y in range(0, shape[1]):
  10.             out+=(int(img[x+2,y])-int(img[x,y]))**2
  11.     return out

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

  1. ###########################################
  3. def ImageToMatrix(dir,name):
  4.     # 读取图片
  5.     im = Image.open(dir+name)
  6.     # 显示图片
  7.     #im.show()
  8.     width,height = im.size
  9.     im = im.convert("L")
  10.     data = im.getdata()
  11.     data = np.matrix(data,dtype='float')/255.0
  13.     new_data = np.reshape(data,(height,width))
  14.     return new_data
  16. def Brenner(img):
  17.     x, y = img.shape
  18.     D = 0
  19.     for i in range(x-2):
  20.         for j in range(y-2):
  21.             D += (img[i+2, j] - img[i, j])**2
  22.     return D
  24. def TestBrener():
  25.     dir = "D:/document/ZKBH/bug/face/"
  26.     imgList = getAllImg(dir)
  28.     for i in range(len(imgList)):
  29.         frame = ImageToMatrix(dir , imgList[i])
  30.         score = Brenner(frame)
  31.         print(str(imgList[i]) + " is " + str(score))
  37. ###########################################
  39. def ImageToMatrix(dir,name):
  40.     # 读取图片
  41.     im = Image.open(dir+name)
  42.     # 显示图片
  43.     #im.show()
  44.     width,height = im.size
  45.     im = im.convert("L")
  46.     data = im.getdata()
  47.     data = np.matrix(data,dtype='float')/255.0
  49.     new_data = np.reshape(data,(height,width))
  50.     return new_data
  52. def Brenner(img):
  53.     x, y = img.shape
  54.     D = 0
  55.     for i in range(x-2):
  56.         for j in range(y-2):
  57.             D += (img[i+2, j] - img[i, j])**2
  58.     return D
  60. def TestBrener():
  61.     dir = "D:/document/ZKBH/bug/face/"
  62.     imgList = getAllImg(dir)
  64.     for i in range(len(imgList)):
  65.         frame = ImageToMatrix(dir , imgList[i])
  66.         score = Brenner(frame)
  67.         print(str(imgList[i]) + " is " + str(score))
  69. ################################

https://www.cnblogs.com/greentomlee/p/9379471.html

  1. ## 2. Brenner 梯度函数  
  2. Brenner梯度函数是最简单的梯度评价函数，它只是简单的计算相邻两个像素灰度差的平方，该函数定义如下：  
  3. ![](https://ws1.sinaimg.cn/large/cdd040eely1g46bosf58xj20890123yn.jpg)  
  4. 其中：f(x,y) 表示图像f对应像素点(x,y)的灰度值，D(f)为图像清晰度计算结果(下同)。  
  6. **代码：**
  7. ```

def Brenner(img): x, y = img.shape D = 0 for i in range(x-2): for j in range(y-2): D += (img[i+2, j] - img[i, j])**2 return D ``` https://gist.github.com/JuneoXIE/d595028586eec752f4352444fc062c44