def getImageVar ( imgPath ) : image = cv2 . imread ( imgPath ) img2gray = cv2 . cvtColor ( image , cv2 . COLOR_BGR2GRAY ) imageVar = cv2 . Laplacian ( img2gray , cv2 . CV_64F ) . var ( ) return imageVar imageVar = getImageVar ( "tooth/15.jpg" ) print ( imageVar )

2.亮度检测：

• 计算图片在灰度图上的均值和方差，当存在亮度异常时，均值会偏离均值点（可以假设为128），方差也会偏小；通过计算灰度图的均值和方差，就可评估图像是否存在过曝光或曝光不足。

import cv2
import numpy as np
img = cv2.imread('1.jpg')
# 把图片转换为单通道的灰度图
gray_img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# 获取形状以及长宽
img_shape = gray_img.shape
height, width = img_shape[0], img_shape[1]
size = gray_img.size
# 灰度图的直方图
hist = cv2.calcHist([gray_img], [0], None, [256], [0, 256])
# 计算灰度图像素点偏离均值(128)程序
a = 0
ma = 0
#np.full 构造一个数组，用指定值填充其元素
reduce_matrix = np.full((height, width), 128)
shift_value = gray_img - reduce_matrix
shift_sum = np.sum(shift_value)
da = shift_sum / size
# 计算偏离128的平均偏差
for i in range(256):
    ma += (abs(i-128-da) * hist[i])
m = abs(ma / size)
# 亮度系数
k = abs(da) / m
print(k)
if k[0] > 1:
    if da > 0:
        print("过亮")
    else:
        print("过暗")
else:
    print("亮度正常")

3.色偏检测：

• 将RGB图像转变到CIE L a b 空间，其中L 表示图像亮度，a 表示图像红/绿分量，b 表示图像黄/蓝分量。通常存在色偏的图像，在a 和b 分量上的均值会偏离原点很远，方差也会偏小；通过计算图像在a 和b 分量上的均值和方差，就可评估图像是否存在色偏。

import cv2
img = cv2.imread('tooth/10.jpg')
img = cv2.cvtColor(img, cv2.COLOR_BGR2LAB)
l_channel, a_channel, b_channel = cv2.split(img)
h,w,_ = img.shape
da = a_channel.sum()/(h*w)-128
db = b_channel.sum()/(h*w)-128
histA = [0]*256
histB = [0]*256
for i in range(h):
    for j in range(w):
        ta = a_channel[i][j]
        tb = b_channel[i][j]
        histA[ta] += 1
        histB[tb] += 1
msqA = 0
msqB = 0
for y in range(256):
    msqA += float(abs(y-128-da))*histA[y]/(w*h)
    msqB += float(abs(y - 128 - db)) * histB[y] / (w * h)
import math
result = math.sqrt(da*da+db*db)/math.sqrt(msqA*msqA+msqB*msqB)
print("d/m = %s"%result)

参考链接：清晰度检测： https://blog.csdn.net/qq_42238397/article/details/81745600
亮度检测： https://blog.csdn.net/qq_40790959/article/details/106107574
色偏检测：
https://blog.csdn.net/sparrowwf/article/details/86595162
https://blog.csdn.net/fightingforcv/article/details/52724848

1.清晰度检测：利用拉普拉斯算子计算图片的二阶导数，反映图片的边缘信息，同样事物的图片，清晰度高的，相对应的经过拉普拉斯算子滤波后的图片的方差也就越大。import cv2#利用拉普拉斯def getImageVar(imgPath): image = cv2.imread(imgPath) img2gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY) imageVar = cv2.Laplacian(img2gray, cv2.C from tools import calLaplacianVar,overExposeDetect def check_image(img_path, fixedSize, stdTimes = 1): #正常值区间 # distArea def getImageVar(imgPath): image = cv2.imread(imgPath) img2gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY) im...