opencv+python 二值化处理threshold（）& adaptivethreshold（）

全局阈值

# 图像二值化 0白色 1黑色
# 全局阈值
def threshold_image(image):
    gray = cv.cvtColor(image, cv.COLOR_BGR2GRAY)
    cv.imshow("original", gray)
    ------------------------------------
    ret, binary = cv.threshold(gray, 0, 255, cv.THRESH_BINARY | cv.THRESH_OTSU)  # 大律法,全局自适应阈值 参数0可改为任意数字但不起作用
    print("阈值：%s" % ret)
    cv.imshow("OTSU", binary)
    -------------------------------------
    ret, binary = cv.threshold(gray, 0, 255,
                               cv.THRESH_BINARY | cv.THRESH_TRIANGLE)  # TRIANGLE法,，全局自适应阈值, 参数0可改为任意数字但不起作用，适用于单个波峰
    print("阈值：%s" % ret)
    cv.imshow("TRIANGLE", binary)
    --------------------------------------
    ret, binary = cv.threshold(gray, 150, 255, cv.THRESH_BINARY)  # 自定义阈值为150,大于150的是白色 小于的是黑色
    print("阈值：%s" % ret)
    cv.imshow("myself", binary)

    ret, binary = cv.threshold(gray, 150, 255, cv.THRESH_BINARY_INV)  # 自定义阈值为150,大于150的是黑色 小于的是白色
    print("阈值：%s" % ret)
    cv.imshow("myself_inv", binary)
    --------------------------------------------
    ret, binary = cv.threshold(gray, 150, 255, cv.THRESH_TRUNC)  # 截断 大于150的是改为150  小于150的保留
    print("阈值：%s" % ret)
    cv.imshow("trunc", binary)

    ret, binary = cv.threshold(gray, 150, 255, cv.THRESH_TOZERO)  # 截断 小于150的是改为150  大于150的保留
    print("阈值：%s" % ret)
    cv.imshow("tozero", binary)

src = cv.imread(r'D:\user\zxh\Desktop\figure1.jpg')
threshold_image(src)
cv.waitKey(0)
cv.destroyAllWindows()

运行结果如下，我们看到原来的风景图片得到不同的处理。注意cv.imshow默认为utf-8编码解码，所以窗口标题最好用英文.

局部阈值

#局部阈值
def local_image(image):
    gray = cv.cvtColor(image, cv.COLOR_BGR2GRAY)
    cv.imshow("original", gray)
    binary1 = cv.adaptiveThreshold(gray, 255, cv.ADAPTIVE_THRESH_MEAN_C, cv.THRESH_BINARY, 25, 10)
    cv.imshow("local1", binary1)
    binary2 = cv.adaptiveThreshold(gray, 255, cv.ADAPTIVE_THRESH_GAUSSIAN_C, cv.THRESH_BINARY, 25, 10)#高斯处理
    cv.imshow("local2", binary2)
src2= cv.imread(r'D:\user\zxh\Desktop\figure1.jpg')
local_image(src2)
cv.waitKey(0)
cv.destroyAllWindows()

cv.ADAPTIVE_THRESH_MEAN_C 和 cv.ADAPTIVE_THRESH_GAUSSIAN_C
图像处理结果如下：

求图像均值寻找阈值

# 求出图像均值作为阈值来二值化
def custom_image(image):
    gray = cv.cvtColor(image, cv.COLOR_BGR2GRAY)
    cv.imshow("original", gray)
    h, w = gray.shape[:2]
    m = np.reshape(gray, [1, w * h])  # 化为一维数组
    mean = m.sum() / (w * h)
    print("mean: ", mean)
    ret, binary = cv.threshold(gray, mean, 255, cv.THRESH_BINARY)
    cv.imshow("binary", binary)

src3 = cv.imread(r'D:\user\zxh\Desktop\figure1.jpg')
custom_image(src3)
cv.waitKey(0)

求得阈值为165.8，图像如下

它的阈值介于OTSU和TRIANGLE之间，经过观察，图像的特点也恰好介于两者之间。