Tensorflow 新手入门之4位数字字母验证码识别

最新推荐文章于 2021-10-04 10:50:20 发布

萌新请大佬吃矛

最新推荐文章于 2021-10-04 10:50:20 发布

阅读量1.2k

点赞数

分类专栏：深度学习文章标签： Tensorflow 深度学习数字验证码字母验证码

本文链接：https://blog.csdn.net/weixin_42589350/article/details/89493333

版权

在无GPU环境下，使用Tensorflow进行CPU训练，实现了4位数字字母验证码的识别，最终精度超91%，数字识别精度更是超过99%。训练设置要求模型准确率超过0.99时结束并保存。

摘要由CSDN通过智能技术生成

Tensorflow 新手入门之4位数字字母验证码识别

用的是ImageCaptcha自动生成的图片

# coding=gbk
import numpy as np
import tensorflow as tf
from captcha.image import ImageCaptcha
import matplotlib.pyplot as plt
from PIL import Image
import random
from tensorflow.python.framework.dtypes import string
from numpy import char

#只做4位数字的识别
number = ['0', '1', '2', '3', '4', '5', '6', '7', '8', '9']
alphabet = ['a','b','c','d','e','f','g','h','i','j','k','l','m','n','o','p','q','r','s','t','u','v','w','x','y','z']
ALPHABET = ['A','B','C','D','E','F','G','H','I','J','K','L','M','N','O','P','Q','R','S','T','U','V','W','X','Y','Z']


keep_prob = tf.placeholder(tf.float32)  # dropout

def random_captcha_text(char_set=number + alphabet + ALPHABET , captcha_size=4):
    captcha_text = []
    for i in range(captcha_size):
        c = random.choice(char_set)
        captcha_text.append(c)
    return captcha_text

def gen_captcha_text_and_image():
    image=ImageCaptcha()  #生成随机图片
    captcha_text=random_captcha_text()
    captcha_text=''.join(captcha_text)
    captcha=image.generate(captcha_text)

    captcha_image=Image.open(captcha)
    captcha_image=np.array(captcha_image)
    return  captcha_text,captcha_image

def conver2gray(img):
    if len(img.shape)>2:
        gray=np.mean(img,-1)
        return gray
    else:return img

def text2vec(text):
    text_len=len(text)
    if text_len>MAX_CAPTCHA:
        raise ValueError('longer than 4')
    
    vector=np.zeros(MAX_CAPTCHA*CHAR_SET_LEN)
 
    def char2pos(c):
        if c == '_':
            k = 62
            return k
        k = ord(c) - 48
        if k > 9:
            k = ord(c) - 55
            if k > 35:
                k = ord(c) - 61
                if k > 61:
                    raise ValueError('No Map')
        return k
     
    for i,c in enumerate(text):
        idx=i*CHAR_SET_LEN+char2pos(c) #[1,0,0,0,0,0,0,0,0,0,0,0,0,1,0,0,0....]一共四十个元素 里面只有四个元素为1
        vector[idx]=1
    return vector

def vec2text(vec):
    text=[]
    char_pos=vec