如何通过 Serverless 轻松识别验证码？
责编 | 晋兆雨
头图 | 付费下载于视觉中国
前言
# coding:utf-8
import random
import numpy
as np
from PIL
import Image
from captcha.image
import ImageCaptcha
CAPTCHA_LIST = [eve
for eve
in
"0123456789abcdefghijklmnopqrsruvwxyzABCDEFGHIJKLMOPQRSTUVWXYZ"]
CAPTCHA_LEN =
4
# 验证码长度
CAPTCHA_HEIGHT =
60
# 验证码高度
CAPTCHA_WIDTH =
160
# 验证码宽度
randomCaptchaText =
lambda char=CAPTCHA_LIST, size=CAPTCHA_LEN:
"".join([random.choice(char)
for _
in range(size)])
def genCaptchaTextImage(width=CAPTCHA_WIDTH, height=CAPTCHA_HEIGHT, save=None):
image = ImageCaptcha(width=width, height=height)
captchaText = randomCaptchaText()
if save:
image.write(captchaText,
'./img/%s.jpg' % captchaText)
return captchaText, np.array(Image.open(image.generate(captchaText)))
print(genCaptchaTextImage(save=
True))
# -*- coding:utf-8 -*-
import numpy
as np
from captcha_gen
import genCaptchaTextImage
from captcha_gen
import CAPTCHA_LIST, CAPTCHA_LEN, CAPTCHA_HEIGHT, CAPTCHA_WIDTH
# 图片转为黑白，3维转1维
convert2Gray =
lambda img: np.mean(img,
-1)
if len(img.shape) >
2
else img
# 验证码向量转为文本
vec2Text =
lambda vec, captcha_list=CAPTCHA_LIST:
''.join([captcha_list[int(v)]
for v
in vec])
def text2Vec(text, captchaLen=CAPTCHA_LEN, captchaList=CAPTCHA_LIST):
"""
验证码文本转为向量
"""
vector = np.zeros(captchaLen * len(captchaList))
for i
in range(len(text)):
vector[captchaList.index(text[i]) + i * len(captchaList)] =
1
return vector
def getNextBatch(batchCount=60, width=CAPTCHA_WIDTH, height=CAPTCHA_HEIGHT):
"""
获取训练图片组
"""
batchX = np.zeros([batchCount, width * height])
batchY = np.zeros([batchCount, CAPTCHA_LEN * len(CAPTCHA_LIST)])
for i
in range(batchCount):
text, image = genCaptchaTextImage()
image = convert2Gray(image)
# 将图片数组一维化 同时将文本也对应在两个二维组的同一行
batchX[i, :] = image.flatten() /
255
batchY[i, :] = text2Vec(text)
return batchX, batchY
# print(getNextBatch(batch_count=1))
# -*- coding:utf-8 -*-
import tensorflow.compat.v1
as tf
from datetime
import datetime
from util
import getNextBatch
from captcha_gen
import CAPTCHA_HEIGHT, CAPTCHA_WIDTH, CAPTCHA_LEN, CAPTCHA_LIST
tf.compat.v1.disable_eager_execution()
variable =
lambda shape, alpha=
0.01: tf.Variable(alpha * tf.random_normal(shape))
conv2d =
lambda x, w: tf.nn.conv2d(x, w, strides=[
1,
1,
1,
1], padding=
'SAME')
maxPool2x2 =
lambda x: tf.nn.max_pool(x, ksize=[
1,
2,
2,
1], strides=[
1,
2,
2,
1], padding=
'SAME')
optimizeGraph =
lambda y, y_conv: tf.train.AdamOptimizer(
1e-3).minimize(
tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(labels=y, logits=y_conv)))
hDrop =
lambda image, weight, bias, keepProb: tf.nn.dropout(
maxPool2x2(tf.nn.relu(conv2d(image, variable(weight,
0.01)) + variable(bias,
0.1))), keepProb)
def cnnGraph(x, keepProb, size, captchaList=CAPTCHA_LIST, captchaLen=CAPTCHA_LEN):
"""
三层卷积神经网络
"""
imageHeight, imageWidth = size
xImage = tf.reshape(x, shape=[
-1, imageHeight, imageWidth,
1])
hDrop1 = hDrop(xImage, [
3,
3,
1,
32], [
32], keepProb)
hDrop2 = hDrop(hDrop1, [
3,
3,
32,
64], [
64], keepProb)
hDrop3 = hDrop(hDrop2, [
3,
3,
64,
64], [
64], keepProb)
# 全连接层
imageHeight = int(hDrop3.shape[
1])
imageWidth = int(hDrop3.shape[
2])
wFc = variable([imageHeight * imageWidth *
64,
1024],
0.01)
# 上一层有64个神经元 全连接层有1024个神经元
bFc = variable([
1024],
0.1)
hDrop3Re = tf.reshape(hDrop3, [
-1, imageHeight * imageWidth *
64])
hFc = tf.nn.relu(tf.matmul(hDrop3Re, wFc) + bFc)
hDropFc = tf.nn.dropout(hFc, keepProb)
# 输出层
wOut = variable([
1024, len(captchaList) * captchaLen],
0.01)
bOut = variable([len(captchaList) * captchaLen],
0.1)
yConv = tf.matmul(hDropFc, wOut) + bOut
return yConv
def accuracyGraph(y, yConv, width=len(CAPTCHA_LIST), height=CAPTCHA_LEN):
"""
偏差计算图，正确值和预测值，计算准确度
"""
maxPredictIdx = tf.argmax(tf.reshape(yConv, [
-1, height, width]),
2)
maxLabelIdx = tf.argmax(tf.reshape(y, [
-1, height, width]),
2)
correct = tf.equal(maxPredictIdx, maxLabelIdx)
# 判断是否相等
return tf.reduce_mean(tf.cast(correct, tf.float32))
def train(height=CAPTCHA_HEIGHT, width=CAPTCHA_WIDTH, ySize=len(CAPTCHA_LIST) * CAPTCHA_LEN):
"""
cnn训练
"""
accRate =
0.95
x = tf.placeholder(tf.float32, [
None, height * width])
y = tf.placeholder(tf.float32, [
None, ySize])
keepProb = tf.placeholder(tf.float32)
yConv = cnnGraph(x, keepProb, (height, width))
optimizer = optimizeGraph(y, yConv)
accuracy = accuracyGraph(y, yConv)
saver = tf.train.Saver()
with tf.Session()
as sess:
sess.run(tf.global_variables_initializer())
# 初始化
step =
0
# 步数
while
True:
batchX, batchY = getNextBatch(
64)
sess.run(optimizer, feed_dict={x: batchX, y: batchY, keepProb:
0.75})
# 每训练一百次测试一次
if step %
100 ==
0:
batchXTest, batchYTest = getNextBatch(
100)
acc = sess.run(accuracy, feed_dict={x: batchXTest, y: batchYTest, keepProb:
1.0})
print(datetime.now().strftime(
'%c'),
' step:', step,
' accuracy:', acc)
# 准确率满足要求，保存模型
if acc > accRate:
modelPath =
"./model/captcha.model"
saver.save(sess, modelPath, global_step=step)
accRate +=
0.01
if accRate >
0.90:
break
step = step +
1
train()
if accRate >
0.90:
break
# -*- coding:utf-8 -*-
# 核心后端服务
import base64
import json
import uuid
import tensorflow
as tf
import random
import numpy
as np
from PIL
import Image
from captcha.image
import ImageCaptcha
# Response
class Response:
def __init__(self, start_response, response, errorCode=None):
self.start = start_response
responseBody = {
'Error': {
"Code": errorCode,
"Message": response},
}
if errorCode
else {
'Response': response
}
# 默认增加uuid，便于后期定位
responseBody[
'ResponseId'] = str(uuid.uuid1())
print(
"Response: ", json.dumps(responseBody))
self.response = json.dumps(responseBody)
def __iter__(self):
status =
'200'
response_headers = [(
'Content-type',
'application/json; charset=UTF-8')]
self.start(status, response_headers)
yield self.response.encode(
"utf-8")
CAPTCHA_LIST = [eve
for eve
in
"0123456789abcdefghijklmnopqrsruvwxyzABCDEFGHIJKLMOPQRSTUVWXYZ"]
CAPTCHA_LEN =
4
# 验证码长度
CAPTCHA_HEIGHT =
60
# 验证码高度
CAPTCHA_WIDTH =
160
# 验证码宽度
# 随机字符串
randomStr =
lambda num=
5:
"".join(random.sample(
'abcdefghijklmnopqrstuvwxyz', num))
randomCaptchaText =
lambda char=CAPTCHA_LIST, size=CAPTCHA_LEN:
"".join([random.choice(char)
for _
in range(size)])
# 图片转为黑白，3维转1维
convert2Gray =
lambda img: np.mean(img,
-1)
if len(img.shape) >
2
else img
# 验证码向量转为文本
vec2Text =
lambda vec, captcha_list=CAPTCHA_LIST:
''.join([captcha_list[int(v)]
for v
in vec])
variable =
lambda shape, alpha=
0.01: tf.Variable(alpha * tf.random_normal(shape))
conv2d =
lambda x, w: tf.nn.conv2d(x, w, strides=[
1,
1,
1,
1], padding=
'SAME')
maxPool2x2 =
lambda x: tf.nn.max_pool(x, ksize=[
1,
2,
2,
1], strides=[
1,
2,
2,
1], padding=
'SAME')
optimizeGraph =
lambda y, y_conv: tf.train.AdamOptimizer(
1e-3).minimize(
tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(labels=y, logits=y_conv)))
hDrop =
lambda image, weight, bias, keepProb: tf.nn.dropout(
maxPool2x2(tf.nn.relu(conv2d(image, variable(weight,
0.01)) + variable(bias,
0.1))), keepProb)
def genCaptchaTextImage(width=CAPTCHA_WIDTH, height=CAPTCHA_HEIGHT, save=None):
image = ImageCaptcha(width=width, height=height)
captchaText = randomCaptchaText()
if save:
image.write(captchaText, save)
return captchaText, np.array(Image.open(image.generate(captchaText)))
def text2Vec(text, captcha_len=CAPTCHA_LEN, captcha_list=CAPTCHA_LIST):
"""
验证码文本转为向量
"""
vector = np.zeros(captcha_len * len(captcha_list))
for i
in range(len(text)):
vector[captcha_list.index(text[i]) + i * len(captcha_list)] =
1
return vector
def getNextBatch(batch_count=60, width=CAPTCHA_WIDTH, height=CAPTCHA_HEIGHT):
"""
获取训练图片组
"""
batch_x = np.zeros([batch_count, width * height])
batch_y = np.zeros([batch_count, CAPTCHA_LEN * len(CAPTCHA_LIST)])
for i
in range(batch_count):
text, image = genCaptchaTextImage()
image = convert2Gray(image)
# 将图片数组一维化 同时将文本也对应在两个二维组的同一行
batch_x[i, :] = image.flatten() /
255
batch_y[i, :] = text2Vec(text)
return batch_x, batch_y
def cnnGraph(x, keepProb, size, captchaList=CAPTCHA_LIST, captchaLen=CAPTCHA_LEN):
"""
三层卷积神经网络
"""
imageHeight, imageWidth = size
xImage = tf.reshape(x, shape=[
-1, imageHeight, imageWidth,
1])
hDrop1 = hDrop(xImage, [
3,
3,
1,
32], [
32], keepProb)
hDrop2 = hDrop(hDrop1, [
3,
3,
32,
64], [
64], keepProb)
hDrop3 = hDrop(hDrop2, [
3,
3,
64,
64], [
64], keepProb)
# 全连接层
imageHeight = int(hDrop3.shape[
1])
imageWidth = int(hDrop3.shape[
2])
wFc = variable([imageHeight * imageWidth *
64,
1024],
0.01)
# 上一层有64个神经元 全连接层有1024个神经元
bFc = variable([
1024],
0.1)
hDrop3Re = tf.reshape(hDrop3, [
-1, imageHeight * imageWidth *
64])
hFc = tf.nn.relu(tf.matmul(hDrop3Re, wFc) + bFc)
hDropFc = tf.nn.dropout(hFc, keepProb)
# 输出层
wOut = variable([
1024, len(captchaList) * captchaLen],
0.01)
bOut = variable([len(captchaList) * captchaLen],
0.1)
yConv = tf.matmul(hDropFc, wOut) + bOut
return yConv
def captcha2Text(image_list):
"""
验证码图片转化为文本
"""
with tf.Session()
as sess:
saver.restore(sess, tf.train.latest_checkpoint(
'model/'))
predict = tf.argmax(tf.reshape(yConv, [
-1, CAPTCHA_LEN, len(CAPTCHA_LIST)]),
2)
vector_list = sess.run(predict, feed_dict={x: image_list, keepProb:
1})
vector_list = vector_list.tolist()
text_list = [vec2Text(vector)
for vector
in vector_list]
return text_list
x = tf.placeholder(tf.float32, [
None, CAPTCHA_HEIGHT * CAPTCHA_WIDTH])
keepProb = tf.placeholder(tf.float32)
yConv = cnnGraph(x, keepProb, (CAPTCHA_HEIGHT, CAPTCHA_WIDTH))
saver = tf.train.Saver()
def handler(environ, start_response):
try:
request_body_size = int(environ.get(
'CONTENT_LENGTH',
0))
except (ValueError):
request_body_size =
0
requestBody = json.loads(environ[
'wsgi.input'].read(request_body_size).decode(
"utf-8"))
imageName = randomStr(
10)
imagePath =
"/tmp/" + imageName
print(
"requestBody: ", requestBody)
reqType = requestBody.get(
"type",
None)
if reqType ==
"get_captcha":
genCaptchaTextImage(save=imagePath)
with open(imagePath,
'rb')
as f:
data = base64.b64encode(f.read()).decode()
return Response(start_response, {
'image': data})
if reqType ==
"get_text":
# 图片获取
print(
"Get pucture")
imageData = base64.b64decode(requestBody[
"image"])
with open(imagePath,
'wb')
as f:
f.write(imageData)
# 开始预测
img = Image.open(imageName)
img = img.resize((
160,
60), Image.ANTIALIAS)
img = img.convert(
"RGB")
img = np.asarray(img)
image = convert2Gray(img)
image = image.flatten() /
255
return Response(start_response, {
'result': captcha2Text([image])})
tensorflow==
1.13.
1
numpy==
1.19.
4
scipy==
1.5.
4
pillow==
8.0.
1
captcha==
0.3
# -*- coding:utf
-8 -*-
import os
import json
from bottle
import route, run, static_file, request
import urllib.request
url =
"http://" + os.environ.
get(
"url")
@route('/')
def index():
return static_file(
"index.html", root=
'html/')
@route('/get_captcha')
def getCaptcha():
data = json.dumps({
"type":
"get_captcha"}).encode(
"utf-8")
reqAttr = urllib.request.Request(
data=
data, url=url)
return urllib.request.urlopen(reqAttr).read().decode(
"utf-8")
@route('/get_captcha_result', method='POST')
def getCaptcha():
data = json.dumps({
"type":
"get_text",
"image": json.loads(request.body.read().decode(
"utf-8"))[
"image"]}).encode(
"utf-8")
reqAttr = urllib.request.Request(
data=
data, url=url)
return urllib.request.urlopen(reqAttr).read().decode(
"utf-8")
run(host=
'0.0.0.0', debug=False, port=
9000)
bottle==
0.12.
19
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<title>验证码识别测试系统
</title>
<link href="https://www.bootcss.com/p/layoutit/css/bootstrap-combined.min.css" rel="stylesheet">
<script>
var image = undefined
function getCaptcha() {
const xmlhttp = window.XMLHttpRequest ? new XMLHttpRequest() : new ActiveXObject("Microsoft.XMLHTTP");
xmlhttp.open("GET", '/get_captcha', false);
xmlhttp.onreadystatechange = function () {
if (xmlhttp.readyState == 4 && xmlhttp.status == 200) {
image = JSON.parse(xmlhttp.responseText).Response.image
document.getElementById("captcha").src = "data:image/png;base64," + image
document.getElementById("getResult").style.visibility = 'visible'
}
}
xmlhttp.setRequestHeader("Content-type", "application/json");
xmlhttp.send();
}
function getCaptchaResult() {
const xmlhttp = window.XMLHttpRequest ? new XMLHttpRequest() : new ActiveXObject("Microsoft.XMLHTTP");
xmlhttp.open("POST", '/get_captcha_result', false);
xmlhttp.onreadystatechange = function () {
if (xmlhttp.readyState == 4 && xmlhttp.status == 200) {
document.getElementById("result").innerText = "识别结果：" + JSON.parse(xmlhttp.responseText).Response.result
}
}
xmlhttp.setRequestHeader("Content-type", "application/json");
xmlhttp.send(JSON.stringify({"image": image}));
}
</script>
</head>
<body>
<div class="container-fluid" style="margin-top: 10px">
<div class="row-fluid">
<div class="span12">
<center>
<h3>
验证码识别测试系统
</h3>
</center>
</div>
</div>
<div class="row-fluid">
<div class="span2">
</div>
<div class="span8">
<center>
<img src="" id="captcha"/>
<br><br>
<p id="result"></p>
</center>
<fieldset>
<legend>操作：
</legend>
<button class="btn" onclick="getCaptcha()">获取验证码
</button>
<button class="btn" onclick="getCaptchaResult()" id="getResult" style="visibility: hidden">识别验证码
</button>
</fieldset>
</div>
<div class="span2">
</div>
</div>
</div>
</body>
</html>
Global:
Service:
Name: ServerlessBook
Description: Serverless图书案例
Log: Auto
Nas: Auto
ServerlessBookCaptchaDemo:
Component: fc
Provider: alibaba
Access:
release
Extends:
deploy:
- Hook: s
install docker
Path: ./
Pre:
true
Properties:
Region: cn-beijing
Service: ${Global.Service}
Function:
Name: serverless_captcha
Description: 验证码识别
CodeUri:
Src: ./src/backend
Excludes:
- src/backend/.fun
- src/backend/
model
Handler: index.handler
Environment:
-
Key: PYTHONUSERBASE
Value: /mnt/
auto/.fun/python
MemorySize:
3072
Runtime: python3
Timeout:
60
Triggers:
-
Name: ImageAI
Type:
HTTP
Parameters:
AuthType: ANONYMOUS
Methods:
-
GET
- POST
- PUT
Domains:
-
Domain:
Auto
ServerlessBookCaptchaWebsiteDemo:
Component: bottle
Provider: alibaba
Access:
release
Extends:
deploy:
- Hook: pip3
install -r requirements.txt -t ./
Path: ./src/website
Pre:
true
Properties:
Region: cn-beijing
CodeUri: ./src/website
App: index.py
Environment:
-
Key:
url
Value: ${ServerlessBookCaptchaDemo.Output.Triggers[
0].Domains[
0]}
Detail:
Service: ${Global.Service}
Function:
Name: serverless_captcha_website
| - src
# 项目目录
| | - backend
# 项目后端，核心接口
| | - index.py
# 后端核心代码
| | - requirements.txt
# 后端核心代码依赖
| | - website
# 项目前端，便于测试使用
| | - html
# 项目前端页面
| | - index.html
# 项目前端页面
| | - index.py
# 项目前端的后台服务（bottle框架）
| | - requirements.txt
# 项目前端的后台服务依赖
s deploy
-
Github 地址： https://github.com/serverless-devs -
Gitee 地址： https://gitee.com/organizations/serverless-devs/projects -
Serverless Devs 官网： https://www.serverless-devs.com
更多阅读推荐
-
-
-
-
带你一文看懂 Blockchain + NoSQL数据库 -