python验证码处理教程（python简单验证码识别的实现方法）
时间：2021-10-07 00:55:48 类别：脚本大全 浏览量：250
python验证码处理教程
python简单验证码识别的实现方法利用svm向量机进行4位数字验证码识别
主要是思路和步骤如下：
一，素材收集
检查环境是否包含有相应的库：
1.在cmd中，通过 pip list命令查看安装的库
2.再使用pip installrequests 安装requests库
3.再次使用pip list 命令
4.利用python获取验证码资源
编写代码：_downloadpic.py
|
|
#!/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urldef 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 + '.jpg" alt="python验证码处理教程（python简单验证码识别的实现方法）" border="0" /> #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) |
二，素材处理
1.二值化处理，增加对比度，锐化，增加亮度，滤镜，转为黑白
2.去除噪点
3.切割图片
编写代码：_picdealwith.py
|
|
#!/usr/bin/env python3import osimport os.pathfrom pil import image, imageenhance, imagefilterimport 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.jpg" alt="python验证码处理教程（python简单验证码识别的实现方法）" border="0" /> strimgpath = os.path.join(strstep2dir, strimgname) img.save(strimgpath) g_count += 1 print("ok！")if __name__ == '__mian__': main() |
三，手工分类
将第二步切割好的图片进行分类，体力活
四，利用svm向量机建立模型
1.安装svm库
下载libsvm库，并解压
将库中的windows目录的路径添加到path环境变量中
将libsvm下的python文件夹中的svm.py和svmutil.py文件拷贝到你的python的路径中lib文件夹中
|
|
from svmutil import * |
2.生成模型文件
2.1.将分好类的图片信息进行提取，生成特征值
2.2.输出向量数据
2.3.根据数据输出svm模型文件
编写代码：_svmdemo.py
|
|
#!/usr/bin/env python3#svm,验证码识别import osimport sysimport randomimport os.pathfrom pil import image, imageenhance, imagefilterfrom 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')
您可能感兴趣
热门推荐
排行榜
|