1200字范文,内容丰富有趣,写作的好帮手!
1200字范文 > 机器学习项目案例 简单的数字验证码自动识别

机器学习项目案例 简单的数字验证码自动识别

时间:2023-01-27 11:35:34

相关推荐

机器学习项目案例  简单的数字验证码自动识别

本篇文章将实现一个识别验证码的案例。

基本思路及步骤:

1.先写一个关于验证码生成器的代码,得到一个有关验证码的库

2.对验证码库中的验证码图片进行处理并对其分割

3.训练数据,得到模型

4.对未知的验证码图片进行预测

由于目前的验证码的形式比较多样,但是验证的思路都是类似的,因此就先从简单的数字开始进行识别。我们先需要写一个验证码生成器,生成验证码库。

验证码需要有5个数字,并且有不同的颜色,还要再图片上加一些噪点和一些随机的线。

代码如下:

from PIL import Imagefrom PIL import ImageDrawfrom PIL import ImageFontimport randomdef getRandomColor():"""获取一个随机颜色(r,g,b)格式的:return:"""c1 = random.randint(0, 255)c2 = random.randint(0, 255)c3 = random.randint(0, 255)if c1 == 255:c1 = 0if c2 == 255:c2 = 0if c3 == 255:c3 = 0return(c1, c2, c3)def getRandomStr():"""获取一个随机数字,每个数字的颜色也是随机的:return:"""random_num = str(random.randint(0, 9))return random_numdef generate_captcha():# 获取一个Image对象,参数分别是RGB模式。宽150,高30, 随机颜色image = Image.new('RGB', (150, 50), (255,255,255))# 获取一个画笔对象,将图片对象传过去draw = ImageDraw.Draw(image)# 获取一个font字体对象参数是ttf的字体文件的目录,以及字体的大小font = ImageFont.truetype("ARLRDBD.TTF", size=32)label = ""for i in range(5):random_char = getRandomStr()label += random_char# 在图片上写东西,参数是:定位,字符串,颜色,字体draw.text((10+i*30, 0), random_char, getRandomColor(), font=font)# 噪点噪线width = 150height = 30# 画线for i in range(3):x1 = random.randint(0, width)x2 = random.randint(0, width)y1 = random.randint(0, height)y2 = random.randint(0, height)draw.line((x1, y1, x2, y2), fill=(0, 0, 0))# 画点for i in range(5):draw.point([random.randint(0, width), random.randint(0, height)], fill=getRandomColor())x = random.randint(0, width)y = random.randint(0, height)draw.arc((x, y, x + 4, y + 4), 0, 90, fill=(0, 0, 0))# 保存到硬盘,名为test.png格式为png的图片image.save(open(''.join(['captcha_images/', label, '.png']), 'wb'), 'png')# image.save(open(''.join(['captcha_predict/', label, '.png']), 'wb'), 'png')if __name__ == '__main__':for i in range(150):generate_captcha()

运行程序之后生成150个验证码图片,会将验证码保存到文件夹中,相当于一个库,如下:

生成验证码之后,我们需要对验证码图片进行处理,具体处理的步骤如下:

1.对验证码图片二值化,首先把图像从RGB 三通道转化成Gray单通道,然后把灰度图(0~255)转化成二值图(0,1)。

2.对二值化验证码图片进行降噪处理,把干扰的点和线去掉

3.对处理后的验证码图片进行分割,根据像素格,把图片中的所有(5个)数字,分别保存到对应的0~9文件夹下。

具体代码如下:

from PIL import Imageimport numpy as npimport matplotlib.pyplot as pltimport osdef binarization(path):img = Image.open(path)img_gray = img.convert('L')img_gray = np.array(img_gray)w, h = img_gray.shapefor x in range(w):for y in range(h):gray = img_gray[x, y]if gray <= 220:img_gray[x, y] = 0else:img_gray[x, y] = 1return img_gray# plt.figure('')# plt.imshow(img_gray, cmap='gray')# plt.axis('off')# plt.show()def noiseReduction(img_gray, label):height, width = img_gray.shapefor x in range(height-1):for y in range(width-1):cnt = 0if img_gray[x, y] == 1:continueelse:for i in [-1, 0, 1]:n = xn += iif n < 0:n = 0for j in [-1, 0, 1]:m = ym += jif m < 0:m = 0if img_gray[n, m] == 0:cnt += 1if cnt <= 4:img_gray[x, y] = 1plt.figure('')plt.imshow(img_gray, cmap='gray')plt.axis('off')plt.savefig(''.join(['clean_captcha_img/', label, '.png']))def img_2_clean():captchas = os.listdir(''.join(['captcha_images/']))for captcha in captchas:label = captcha.split('.')[0]img_path = ''.join(['captcha_images/', captcha])im = binarization(img_path)noiseReduction(im, label)def cutImg(label):labels = list(label)img = Image.open(''.join(['clean_captcha_img/', label, '.png']))for i in range(5):pic = img.crop((100*(1+i), 170, 100*(1+i)+100, 280))plt.imshow(pic)seq = get_save_seq(label[i])pic.save(''.join(['cut_number/', str(label[i]), '/', str(seq), '.png']))def get_save_seq(num):numlist = os.listdir(''.join(['cut_number/', num, '/']))if len(numlist) == 0 or numlist is None:return 0else:max_file = 0for file in numlist:if int(file.split('.')[0]) > max_file:max_file = int(file.split('.')[0])return int(max_file)+1def create_dir():for i in range(10):os.makedirs(''.join(['cut_number/', str(i)]))def clean2cut():clean_img = os.listdir(''.join(['clean_captcha_img/']))for img in clean_img:label = img.split('.')[0]cutImg(label)if __name__ == '__main__':img_2_clean()create_dir()clean2cut()

二值化并且降噪后的图片如下:

切割后的图片会保存在对应的数字文件夹中,

比如切割后的数字 6 如下:

1.把数据带入逻辑回归进行建模

(1)把切割好的数据,按照x(二位数组),y(一维数组)的方式传入logisticRegression.fit()函数进行拟合

我们可以通过网格搜索(GridSearch)来进行调参

(2)通过joblib包,把模型保存到本地

2.得到模型后,进行图像验证

(1)根据之前处理图像的步骤,重复操作新的图像

(2)对切割好的每个图像,独立的进行预测

(3)把最后预测结果进行拼接

注意在代码中需要导入之前写的函数,

代码如下:

import osfrom PIL import Imageimport numpy as npfrom sklearn.model_selection import train_test_splitfrom sklearn.linear_model import LogisticRegressionfrom sklearn.externals import joblibfrom CAPTCHA.captcha_logistic import *def load_data():# 假设20*5像素块构成 20*5 = 100# [[11...1111]# [111...111]# ....# [11111111]]# X = [[11111.....11111]] 100位 Y = [0]X, Y = [], []cut_list = os.listdir('cut_number')for numC in cut_list:num_list_dir = ''.join(['cut_number/', str(numC), '/'])nums_dir = os.listdir(num_list_dir)for num_file in nums_dir:img = Image.open(''.join(['cut_number/', str(numC), '/', num_file]))img_gray = img.convert('L')img_array = np.array(img_gray)w, h = img_array.shapefor x in range(w):for y in range(h):gray = img_array[x, y]if gray <= 240:img_array[x, y] = 0else:img_array[x, y] = 1img_re = img_array.reshape(1, -1)X.append(img_re[0])Y.append(int(numC))return np.array(X), np.array(Y)def generate_model(X, Y):X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.3)log_clf = LogisticRegression(multi_class='ovr', solver='sag', max_iter=10000)# 利用交叉验证选择参数# param_grid = {"tol": [1e-4, 1e-3, 1e-2],#"C": [0.4, 0.6, 0.8]}# grid_search = GridSearchCV(log_clf, param_grid=param_grid, cv=3)# grid_search.fit(X_train, Y_train)log_clf.fit(X_train, Y_train)# 将模型持久化joblib.dump(log_clf, 'captcha_model/captcha_model.model')def get_model():model = joblib.load('captcha_model/captcha_model.model')return modeldef capthca_predict():path = 'captcha_predict/unknown.png'pre_img_gray = binarizaion(path)noiseReduction(pre_img_gray, 'unknown')# cut imagelabels = ['0', '1', '2', '3', '4']img = Image.open(''.join(['clean_captcha_img/unknown.png']))for i in range(5):pic = img.crop((100*(1+i), 170, 100*(1+i)+100, 280))plt.imshow(pic)pic.save(''.join(['captcha_predict/', labels[i], '.png']))result = ''model = get_model()for i in range(5):path = ''.join(['captcha_predict/', labels[i], '.png'])img = Image.open(path)img_gray = img.convert('L')img_array = np.array(img_gray)w, h = img_array.shapefor x in range(w):for y in range(h):gray = img_array[x, y]if gray <= 220:img_array[x, y] = 0else:img_array[x, y] = 1img_re = img_array.reshape(1, -1)X = img_re[0]y_pre = model.predict([X])result = ''.join([result, str(y_pre[0])])return resultif __name__ == '__main__':X, Y = load_data()generate_model(X, Y)model = get_model()result = capthca_predict()print(result)

将要预测识别的验证码图片:

最终识别结果:

可以看到对给出的验证码图片进行了成功识别。

本内容不代表本网观点和政治立场,如有侵犯你的权益请联系我们处理。
网友评论
网友评论仅供其表达个人看法,并不表明网站立场。