12306登录验证码识别(Java版)

18 篇文章 0 订阅
6 篇文章 0 订阅

懒惰是程序员的第一生产力

源码地址

1 服务器性能差,不要频繁请求(做了熔断保护处理)
2 上传标准图片
3 添加了爬虫爬取验证功能,设置了ajax返回数据的css样式
在这里插入图片描述

在这里插入图片描述
窝在家里没事干…
python调用方式

  1. 上传图片
import requests
import uuid
url="http://www.dill.fun/image"
#更改verify.jpg为验证图片路径
response=requests.request("POST",url,data={"uuid":uuid.uuid1()},files={'uploadImg':open('verify.jpg','rb')})
print(response.text)

调用结果
在这里插入图片描述

  1. 上传base64码
import requests
import uuid
url="http://www.dill.fun/base64"
base64='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'
response=requests.request("POST",url,data={"base64":base64,"uuid":uuid.uuid1()})
print(response.text)

调用结果
在这里插入图片描述

用keras训练完后转成tensorflow bp文件,通过javaWeb调用输出
支持图片上传方式和base64码方式

这里贴出keras训练代码

  • 字符分类用的lenet
from keras.models import Sequential
from keras.layers import Conv2D, MaxPool2D, Flatten, Dropout, Dense
from keras.losses import categorical_crossentropy
from keras.optimizers import Adadelta

n=80
root="top_"
x=np.load(os.path.join(root,"datasource_image.npy"))/255.0
y=np.load(os.path.join(root,"datasource_label.npy"))
x=x.reshape(x.shape+(1,))
y=to_categorical(y,n)
total_num=len(y)
index = [i for i in range(total_num)]
np.random.shuffle(index) 

x = x[index]
y = y[index]
rate=0.7
split=int(total_num*rate)
train_x,train_y,test_x,test_y=x[:split],y[:split],x[split:],y[split:]
del x,y
print("Train Data Number: {}".format(split))
print("Test Data Number: {}".format(total_num-split))
print("Create Model ...")
model = Sequential()
model.add(Conv2D(32, (5,5), activation='relu', input_shape=[30,60, 1]))
model.add(Conv2D(64, (5,5), activation='relu'))
model.add(Conv2D(64, (5,5), activation='relu'))
model.add(MaxPool2D(pool_size=(2,2)))
model.add(Flatten())
model.add(Dropout(0.5))
model.add(Dense(512, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(n, activation='softmax'))

model.compile(optimizer='adam',
              loss='categorical_crossentropy',
              metrics=['accuracy'])
print("Done.")
print("Start train...")
model.fit(train_x, train_y,batch_size=32, nb_epoch=10, verbose=1,validation_split=0.25,shuffle=True) 
model.save("train-mobilenet-top.h5")
print("Start test...")
loss,acc=model.evaluate( test_x,test_y, batch_size=32, verbose=1, sample_weight=None)
print("loss:{} acc:{} ".format(loss,acc))
  • 图片分类用的mobileNet
from keras.applications.mobilenet import MobileNet
import numpy as np
from keras.utils import to_categorical
import os
from keras.layers import Input



n=80
root="pic_"
x=np.load(os.path.join(root,"datasource_image.npy"))/255.0
y=np.load(os.path.join(root,"datasource_label.npy"))
x=x.reshape(x.shape+(1,))
y=to_categorical(y,n)
total_num=len(y)
index = [i for i in range(total_num)]
np.random.shuffle(index) 

x = x[index]
y = y[index]
rate=0.7
split=int(total_num*rate)
train_x,train_y,test_x,test_y=x[:split],y[:split],x[split:],y[split:]
del x,y
print("Train Data Number: {}".format(split))
print("Test Data Number: {}".format(total_num-split))
print("Create Model ...")
model=MobileNet(
				include_top=True,
				weights=None, 
				input_tensor=Input(shape=(67,68,1)) , 
				pooling=None, 
				classes=n
				)
model.compile(optimizer='adam',
              loss='categorical_crossentropy',
              metrics=['accuracy'])
print("Done.")
print("Start train...")
model.fit(train_x, train_y,batch_size=32, nb_epoch=10, verbose=1,validation_split=0.25,shuffle=True) 
model.save("train-mobilenet.h5")
print("Start test...")
loss,acc=model.evaluate( test_x,test_y, batch_size=32, verbose=1, sample_weight=None)
print("loss:{} acc:{} ".format(loss,acc))

吐槽一句 java做图像处理实在是太麻烦了 我吐了

  • 0
    点赞
  • 9
    收藏
    觉得还不错? 一键收藏
  • 3
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论 3
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值