python 验证码识别示例（二） 复杂验证码识别

在这篇博文中手把手教你如何去分割验证，然后进行识别。

一：下载验证码

验证码分析，图片上有折线，验证码有数字，有英文字母大小写，分类的时候需要更多的样本，验证码的字母是彩色的，图片上有雪花等噪点，因此识别改验证码难度较大

二：二值化和降噪：

三： 切割：

四：分类：

五：   测试识别率

         　　 　　

六：总结：

综合识别率在70%左右，对于这个识别率我觉得还是挺高的，因为这个验证码的识别难度还是很大

代码：

一.  下载图片：

#-*-coding:utf-8-*-
import requestsdef spider():url = "https://www.epailive.com/basic/captcha?ran=0.22070346581876787"for i in range(1, 101):print("正在下载的张数是：",i)with open("./1__get_image/{}.png".format(i), "wb") as f:f.write(requests.get(url).content)
spider()

二： 验证码二值化和降噪：

#-*-coding:utf-8-*-
# coding:utf-8
import sys, os
from PIL import Image, ImageDraw# 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)] = 1else:t2val[(x, y)] = 0# 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
# 输出
#  0：降噪成功
#  1：降噪失败
def clearNoise(image, N, Z):for i in range(0, Z):t2val[(0, 0)] = 1t2val[(image.size[0] - 1, image.size[1] - 1)] = 1for x in range(1, image.size[0] - 1):for y in range(1, image.size[1] - 1):nearDots = 0L = t2val[(x, y)]if L == t2val[(x - 1, y - 1)]:nearDots += 1if L == t2val[(x - 1, y)]:nearDots += 1if L == t2val[(x - 1, y + 1)]:nearDots += 1if L == t2val[(x, y - 1)]:nearDots += 1if L == t2val[(x, y + 1)]:nearDots += 1if L == t2val[(x + 1, y - 1)]:nearDots += 1if L == t2val[(x + 1, y)]:nearDots += 1if L == t2val[(x + 1, y + 1)]:nearDots += 1if nearDots < N:t2val[(x, y)] = 1def 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)for i in range(1, 101):path = "1__get_image/" + str(i) +  ".png"image = Image.open(path)image = image.convert('L')twoValue(image, 198)clearNoise(image, 3, 1)path1 = "2__erzhihua_jiangzao/" + str(i) + ".jpg"saveImage(path1, image.size)

三：  切割验证码：

#-*-coding:utf-8-*-from PIL import Imagedef smartSliceImg(img, outDir, ii,count=4, p_w=3):''':param img::param outDir::param count: 图片中有多少个图片:param p_w: 对切割地方多少像素内进行判断:return:'''w, h = img.sizepixdata = img.load()eachWidth = int(w / count)beforeX = 0for i in range(count):allBCount = []nextXOri = (i + 1) * eachWidthfor x in range(nextXOri - p_w, nextXOri + p_w):if x >= w:x = w - 1if x < 0:x = 0b_count = 0for y in range(h):if pixdata[x, y] == 0:b_count += 1allBCount.append({'x_pos': x, 'count': b_count})sort = sorted(allBCount, key=lambda e: e.get('count'))nextX = sort[0]['x_pos']box = (beforeX, 0, nextX, h)img.crop(box).save(outDir + str(ii) + "_" + str(i) + ".png")beforeX = nextXfor ii in  range(1, 101):path = "2__erzhihua_jiangzao/" + str(ii) + ".jpg"img = Image.open(path)outDir = '3__qiege/'smartSliceImg(img, outDir, ii,count=4, p_w=3)

四： 训练：

#-*-coding:utf-8-*-import numpy as np
import os
import timefrom PIL import Image
from sklearn.externals import joblib
from sklearn.neighbors import KNeighborsClassifierdef load_dataset():X = []y = []for i in "23456789ABVDEFGHKMNPRSTUVWXYZ":target_path = "fenlei/" + iprint(target_path)for title in os.listdir(target_path):pix = np.asarray(Image.open(os.path.join(target_path, title)).convert('L'))X.append(pix.reshape(25 * 30))y.append(target_path.split('/')[-1])X = np.asarray(X)y = np.asarray(y)return X, ydef check_everyone(model):pre_list = []y_list = []for i in "23456789ABCDEFGHKMNPRSTUVWXYZ":part_path = "part/" + ifor title in os.listdir(part_path):pix = np.asarray(Image.open(os.path.join(part_path, title)).convert('L'))pix = pix.reshape(25 * 30)pre_list.append(pix)y_list.append(part_path.split('/')[-1])pre_list = np.asarray(pre_list)y_list = np.asarray(y_list)result_list = model.predict(pre_list)acc = 0for i in result_list == y_list:print(result_list,y_list,)if i == np.bool(True):acc += 1print(acc, acc / len(result_list))X, y = load_dataset()
knn = KNeighborsClassifier()
knn.fit(X, y)
joblib.dump(knn, 'yipai.model')
check_everyone(knn)

五：模型测试：

# -*- coding: utf-8 -*-import numpy as np
from PIL import Image
from sklearn.externals import joblib
import ostarget_path = "1__get_image/"
source_result = []
for title in os.listdir(target_path):source_result.append(title.replace('.png',''))def predict(model):predict_result = []for q in range(1,101):pre_list = []y_list = []for i in range(0,4):part_path = "part1/" + str(q) + "_" + str(i) + ".png"# print(part_path)pix = np.asarray(Image.open(os.path.join(part_path)))pix = pix.reshape(25 * 30)pre_list.append(pix)y_list.append(part_path.split('/')[-1])pre_list = np.asarray(pre_list)y_list = np.asarray(y_list)result_list = model.predict(pre_list)print(result_list,q)predict_result.append(str(result_list[0] + result_list[1] + result_list[2] + result_list[3]))return predict_resultmodel = joblib.load('yipai.model')
predict_result = predict(model)
# print(source_result)
# print(predict_result)