python简单验证码识别的实现方法

#!/usr/bin/nev python3
#利用python从站点下载验证码图片

import requests

## 1.在 http://www.xxx.com
# 获取验证码URL
def Downloads_Pic(strPath, strName):
 #设置url
 url = 'http://www.xxx.com'

 #以二进制方式发送Get请求，
 #将stream = True，
 #数据读取完成前不要断开链接
 rReq = requests.get(url, stream = True)

 #尝试保存图片
 with open(strPath + strName + '.png', 'wb') as fpPic:
  #循环读取1024Byte到byChunk中，读完则跳出
  for byChunk in rReq.iter_content(chunk_size = 1024):
   if byChunk:
    fpPic.write(byChunk)
    fpPic.flush()
  fpPic.close()

for i in range(1, 10 + 1):
 strFileName = "%03d" % i
 Downloads_Pic('D:/1/', strFileName)

#!/usr/bin/env python3
import os
import os.path
from PIL import Image, ImageEnhance, ImageFilter
import random

#二值化处理
#strImgPath 图片路径
def BinaryzationImg(strImgPath):
 #打开图片
 imgOriImg = Image.open(strImgPath)

 #增加对比度
 pocEnhance = ImageEnhance.Contrast(imgOriImg)
 #增加255%对比度
 imgOriImg = pocEnhance.enhance(2.55)

 #锐化
 pocEnhance = ImageEnhance.Sharpness(imgOriImg)
 #锐化200%
 imgOriImg = pocEnhance.enhance(2.0)

 #增加亮度
 pocEnhance = ImageEnhance.Brightness(imgOriImg)
 #增加200%
 imgOriImg = pocEnhance.enhance(2.0)

 #添加滤镜效果
 imgGryImg = imgOriImg.convert('L').filter(ImageFilter.DETAIL)

 #二值化处理
 imgBinImg = imgGryImg.convert('1')

 return imgBinImg

#去除噪点
def ClearNoise(imgBinImg):
 for x in range(1, (imgBinImg.size[0]-1)):
  for y in range(1,(imgBinImg.size[1] - 1)):
  #一个点为黑色，周围8个点为白色，则此点为噪点，设置为白色
   if imgBinImg.getpixel((x, y)) == 0 \
    and imgBinImg.getpixel(((x - 1), (y + 1))) == 255 \
    and imgBinImg.getpixel(((x - 1), y)) == 255 \
    and imgBinImg.getpixel(((x - 1), (y - 1))) == 255 \
    and imgBinImg.getpixel(((x + 1), (y + 1))) == 255 \
    and imgBinImg.getpixel(((x + 1), y)) == 255 \
    and imgBinImg.getpixel(((x + 1), (y - 1))) == 255 \
    and imgBinImg.getpixel((x, (y + 1))) == 255 \
    and imgBinImg.getpixel((x, (y - 1))) == 255:
    imgBinImg.putpixel([x, y], 255)

 return imgBinImg

#切割图片
def GetCropImgs(imgClrImg):
 ImgList = []
 for i in range(4):
  x = 6 + i * 13
  y = 3
  SubImg = imgClrImg.crop((x, y, x + 13, y + 15))
  ImgList.append(SubImg)
 return ImgList


#调用部分
def main():
 g_Count = 0
 strStep1Dir = 'D:/1/step1/'
 strStep2Dir = 'D:/1/step2/'
 for ParentPath, DirName, FileNames in os.walk(strStep1Dir):
  for i in FileNames:
   #图片文件路径信息
   strFullPath = os.path.join(ParentPath, i)
   imgBinImg = BinaryzationImg(strFullPath)
   imgClrImg = ClearNoise(imgBinImg)
   ImgList = GetCropImgs(imgClrImg)
   for img in ImgList:
    strImgName = "%04d%04d.png" % (g_Count, random.randint(0, 9999))
    strImgPath = os.path.join(strStep2Dir, strImgName)
    img.save(strImgPath)
    g_Count += 1

 print("OK！")

if __name__ == '__mian__':
 main()

from svmutil import *

#!/usr/bin/env python3

#SVM,验证码识别

import os
import sys
import random
import os.path
from PIL import Image, ImageEnhance, ImageFilter
from svmutil import *

##记录像素点的值，描述特征，采用遍历每个像素点统计黑色点的数量
def GetFeature(imgCropImg, nImgHeight, nImgWidth):
 PixelCountList = []
 for y in range(nImgHeight):
  CountX = 0
  for x in range(nImgWidth):
   if imgCropImg.getpixel((x, y)) == 0:
    CountX += 1
  PixelCountList.append(CountX)
 for x in range(nImgWidth):
  CountY = 0
  for y in range(nImgHeight):
   if imgCropImg.getpixel((x, y)) == 0:
    CountY += 1
  PixelCountList.append(CountY)
 return PixelCountList

##输出向量数据
def OutPutVectorData(strID, strMaterialDir, strOutPath):
 for ParentPath, DirNames, FileNames in os.walk(strMaterialDir):
  with open(strOutPath, 'a') as fpFea:
   for fp in FileNames:
    #图片文件路径信息
    strFullPath = os.path.join(ParentPath, fp)

    #打开图片
    imgOriImg = Image.open(strFullPath)

    #生成特征值
    FeatureList = GetFeature(imgOriImg, 15, 13)

    strFeature = strID + ' '
    nCount = 1
    for i in FeatureList:
     strFeature = '%s%d:%d ' % (strFeature, nCount, i)
     nCount += 1
    fpFea.write(strFeature + '\n')
    fpFea.flush()
  fpFea.close()

#训练SVM模型
def TrainSvmModel(strProblemPath, strModelPath):
 Y, X = svm_read_problem(strProblemPath)
 Model = svm_train(Y, X)
 svm_save_model(strModelPath, Model)

#SVM模型测试
def SvmModelTest(strProblemPath, strModelPath):
 TestY, TestX = svm_read_problem(strProblemPath)
 Model = svm_load_model(strModelPath)
 #返回识别结果
 pLabel, pAcc, pVal = svm_predict(TestY, TestX, Model)
 return pLabel


##输出测试向量数据
def OutPutTestVectorData(strID, strDir, strOutPath):
 fileList = []
 for parentPath, strDir, fileName in os.walk(strDir):
  fileList = fileName
 with open(strOutPath, 'a') as fpFea:
  for fp in fileList:
   #图片文件路径信息
   strFullPath = os.path.join(parentPath, fp)

   #打开图片
   imgOriImg = Image.open(strFullPath)

   #生成特征值
   FeatureList = GetFeature(imgOriImg, 15, 13)

   strFeature = strID + ' '
   nCount = 1
   for i in FeatureList:
    strFeature = '%s%d:%d ' % (strFeature, nCount, i)
    nCount += 1
   fpFea.write(strFeature + '\n')
   fpFea.flush()
  fpFea.close()


def main():
# 1.循环输出向量文件
 for i in range(0, 10):
  strID = '%d' % i
  OutPutVectorData(strID, 'D:/1/step3/' + strID, 'D:/1/step4/Vector.txt')

# 2.调用函数训练SVM模型
 TrainSvmModel('D:/1/step4/Vector.txt', 'D:/1/step5/Model.txt')
# 3.调用函数识别结果
 pLabel = SvmModelTest('D:/1/step6/Vector.txt', 'D:/1/step5/Model.txt')
 for i in pLabel:
  print('%d' % i)



if __name__ == '__main__':
 main()

#!/usr/bin/env python3
#对一张验证码图片进行识别测试

##1.获取一张验证码图片
##2.对图片进行处理
## 2.1.二值化处理，增加对比度，锐化，增加亮度，滤镜，转为黑白，
## 2.2.去除噪点
## 2.3.切割图片
##3.生成向量文件
##4.再利用之前的模型文件进行识别测试

################
import _PicDealWith
import os
import random
import _SVMDemo


##测试
g_Count = 0
strDirPath = 'D:/1/test/'
strFileName = '001.png'
#1.图片文件路径信息
strFullPath = os.path.join(strDirPath, strFileName)
#2.对图片进行处理
#2.1二值化处理
imgBinImg = _PicDealWith.BinaryzationImg(strFullPath)
#2.2去除噪点
imgClrImg = _PicDealWith.ClearNoise(imgBinImg)
#2.3切割图片
ImgList = _PicDealWith.GetCropImgs(imgClrImg)
#2.3循环写入文件
for img in ImgList:
 strImgName = "%04d%04d.png" % (g_Count, random.randint(0, 9999))
 strImgPath = os.path.join(strDirPath, strImgName)
 img.save(strImgPath)
 g_Count += 1

print("OK")

os.remove(strFullPath)

#3.生成向量文件
_SVMDemo.OutPutTestVectorData('0', 'D:/1/test/', 'D:/1/test/Vector.txt')

#4.利用之前的模型文件进行识别测试
pLabel = _SVMDemo.SvmModelTest('D:/1/test/Vector.txt', 'D:/1/step5/Model.txt')
for i in pLabel:
 print('%d' % i, end = '')