1.可以采用分块方法，

2.先缩放处理就行二值化，然后还原大小

def big_image_binary(image):
    print(image.shape)  #(4208, 2368, 3)　　#超大图像，屏幕无法显示完整
    cw,ch = 256,256
    h,w = image.shape[:2]
    gray = cv.cvtColor(image,cv.COLOR_RGB2GRAY)   #要二值化图像，要先进行灰度化处理
    for row in range(0,h,ch):
        for col in range(0,w,cw):
            roi = gray[row:row+ch,col:col+cw]   #获取分块
            # ret,binary = cv.threshold(roi,0,255,cv.THRESH_BINARY|cv.THRESH_OTSU)　　#全局阈值
            binary = cv.adaptiveThreshold(roi,255,cv.ADAPTIVE_THRESH_GAUSSIAN_C,cv.THRESH_BINARY,127,20)　　#局部阈值
            gray[row:row + ch, col:col + cw] = binary　　#分块覆盖
            print(np.std(binary),np.mean(binary))

    cv.imwrite("binary2.jpg",gray)

ret,binary = cv.threshold(roi,0,255,cv.THRESH_BINARY|cv.THRESH_OTSU)　　#全局阈值

binary = cv.adaptiveThreshold(roi,255,cv.ADAPTIVE_THRESH_GAUSSIAN_C,cv.THRESH_BINARY,127,20)　　#局部阈值

def big_image_binary(image):
    print(image.shape)  #(4208, 2368, 3)
    cw,ch = 128,128
    h,w = image.shape[:2]
    gray = cv.cvtColor(image,cv.COLOR_RGB2GRAY)   #要二值化图像，要先进行灰度化处理
    for row in range(0,h,ch):
        for col in range(0,w,cw):
            roi = gray[row:row+ch,col:col+cw]   #获取分块
            dev = np.std(roi)
            avg = np.mean(roi)
            if dev < 15 and avg > 200:　　#满足条件，接近空白区域，让他变黑
                gray[row:row + ch, col:col + cw] = 0    #全部都赋值为0
            else:
                ret,binary = cv.threshold(roi,0,255,cv.THRESH_BINARY|cv.THRESH_OTSU)
                gray[row:row + ch, col:col + cw] = binary
                print(np.std(binary), np.mean(binary))

    cv.imwrite("binary.jpg",gray)

print(np.std(binary),np.mean(binary))

通过上面获取图像的标准差和平均值，当标准差为0，平均值为255时，代表该区域为空白区域

我们可以将该空白区域（或者满足一定条件的区域），直接设置为0或者255或者其他想要获取的图像，不需要进行多余的阈值二分