python简单识别验证码去噪

验证码多种多样，我这里提供的方法仅对有噪点的验证码进行识别有效。

首先，这是我准备的原始图片 4.png

具体的实现代码

import tesserocr
from PIL import Image, ImageDraw
import time

# image = Image.open("img/4_1.png")
# fh = open("img/1.txt", "w")
# w, h = image.size
# 图片转文本，测试用
# for i in range(h):
#     for j in range(w):
#         cl = image.getpixel((j, i))
#         clall = cl[0] + cl[1] + cl[2]
#         # clall == 0即当前像素为黑色
#         if clall == 0:
#             fh.write("0")
#         else:
#             fh.write("1")
#     fh.write("\n")
# fh.close()

# 将图片转为黑白二色
def black_white(image):
    w, h = image.size
    for i in range(h):
        for j in range(w):
            cl = image.getpixel((j, i))
            clall = cl[0] + cl[1] + cl[2]
            # clall == 0即当前像素为黑色
            if clall >= 155*3:  # 根据具体的图片修改
                image.putpixel((j, i), (255, 255, 255))
            else:
                image.putpixel((j, i), (0, 0, 0))

#二值数组
t2val = {}
def twoValue(image,G):
    for y in range(0,image.size[1]):
        for x in range(0,image.size[0]):
            g = image.getpixel((x,y))
            if g > G:
                t2val[(x,y)] = 1
            else:
                t2val[(x,y)] = 0

# 降噪
# 根据一个点A的RGB值，与周围的8个点的RBG值比较，设定一个值N（0 <N <8），当A的RGB值与周围8个点的RGB相等数小于N时，此点为噪点
# G: Integer 图像二值化阀值 N: Integer 降噪率 0 <N <8 Z: Integer 降噪次数
def clearNoise(image,N,Z):
    for i in range(0,Z):
        t2val[(0,0)] = 1
        t2val[(image.size[0] - 1,image.size[1] - 1)] = 1

        for x in range(1,image.size[0] - 1):
            for y in range(1,image.size[1] - 1):
                nearDots = 0
                L = t2val[(x,y)]
                if L == t2val[(x - 1,y - 1)]:
                    nearDots += 1
                if L == t2val[(x - 1,y)]:
                    nearDots += 1
                if L == t2val[(x- 1,y + 1)]:
                    nearDots += 1
                if L == t2val[(x,y - 1)]:
                    nearDots += 1
                if L == t2val[(x,y + 1)]:
                    nearDots += 1
                if L == t2val[(x + 1,y - 1)]:
                    nearDots += 1
                if L == t2val[(x + 1,y)]:
                    nearDots += 1
                if L == t2val[(x + 1,y + 1)]:
                    nearDots += 1
                if nearDots < N:
                    t2val[(x,y)] = 1

def saveImage(filename,size):
    image = Image.new("1",size)
    draw = ImageDraw.Draw(image)
    for x in range(0,size[0]):
        for y in range(0,size[1]):
            draw.point((x,y),t2val[(x,y)])
    image.save(filename)

def start(img_path,save_img_path):
    image = Image.open(img_path)
    black_white(image)
    image = image.convert("L")
    twoValue(image,100)
    clearNoise(image,4,1)
    saveImage(save_img_path,image.size)
    print(tesserocr.file_to_text(save_img_path))

img_path = "img/4.png"
save_img_path = "img/4_1.png"
start(img_path, save_img_path)

经过处理后得到以下图片 4_1.png

控制台输出结果

ziri

不过以上是在理想情况下的实现，对于某些图片的识别率不高

等后期加上一些算法提高识别率把。

原文地址：https://www.cnblogs.com/YLTzxzy/p/11331128.html