python验证码 识别代码不准_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-*-

importrequestsdefspider():

url= "xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"

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

importsys, osfrom PIL importImage, ImageDraw#二值数组

t2val ={}deftwoValue(image, G):for y in range(0, image.size[1]):for x inrange(0, image.size[0]):

g=image.getpixel((x, y))if g >G:

t2val[(x, y)]= 1

else:

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

defclearNoise(image, N, Z):for i inrange(0, Z):

t2val[(0, 0)]= 1t2val[(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

t2val[(x, y)]= 1

defsaveImage(filename, size):

image= Image.new("1", size)

draw=ImageDraw.Draw(image)for x inrange(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 importImagedef 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.size

pixdata=img.load()

eachWidth= int(w /count)

beforeX=0for i inrange(count):

allBCount=[]

nextXOri= (i + 1) *eachWidthfor x in range(nextXOri - p_w, nextXOri +p_w):if x >=w:

x= w - 1

if x <0:

x=0

b_count=0for y inrange(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-*-

importnumpy as npimportosimporttimefrom PIL importImagefrom sklearn.externals importjoblibfrom sklearn.neighbors importKNeighborsClassifierdefload_dataset():

X=[]

y=[]for i in "23456789ABVDEFGHKMNPRSTUVWXYZ":

target_path= "fenlei/" +iprint(target_path)for title inos.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)returnX, ydefcheck_everyone(model):

pre_list=[]

y_list=[]for i in "23456789ABCDEFGHKMNPRSTUVWXYZ":

part_path= "part/" +ifor title inos.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+= 1

print(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 -*-

importnumpy as npfrom PIL importImagefrom sklearn.externals importjoblibimportos

target_path= "1__get_image/"source_result=[]for title inos.listdir(target_path):

source_result.append(title.replace('.png',''))defpredict(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]))returnpredict_result

model= joblib.load('yipai.model')

predict_result=predict(model)#print(source_result)#print(predict_result)