首先，生成訓練集，用PIL庫生成150張驗證碼圖片

from PIL import Image from PIL import ImageDraw from PIL import ImageFont import randomdef getRandomColor():"""獲取一個隨機顏色(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():"""獲取一個隨機數字，每個數字的顏色也是隨機的:return:"""random_num = str(random.randint(0, 9))return random_numdef generate_captcha():# 獲取一個Image對象，參數分別是RGB模式。寬150，高30， 隨機顏色image = Image.new('RGB', (150, 50), (255,255,255))# 獲取一個畫筆對象，將圖片對象傳過去draw = ImageDraw.Draw(image)# 獲取一個font字體對象參數是ttf的字體文件的目錄，以及字體的大小font = ImageFont.truetype("Lohit-Bengali.ttf", size=32)label = ""for i in range(5):random_char = getRandomStr()label += random_char# 在圖片上寫東西，參數是：定位，字符串，顏色，字體draw.text((10+i*30, 0), random_char, getRandomColor(), font=font)# 噪點噪線width = 150height = 30# 畫線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))# 畫點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))# 保存到硬盤，名為test.png格式為png的圖片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()

對驗證碼進行處理，首先將圖片的RGB值(0～255，0~255，0～255)轉為灰度值，再對灰度值二值化，得到像素點只有黑白（0，1）的圖片，對該圖片降噪，切分，得到訓練集

from PIL import Image import numpy as np import matplotlib.pyplot as plt import osdef binarizaion(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] = 1plt.figure('')plt.imshow(img_gray, cmap='gray')plt.axis('off')plt.show()return img_graydef noiseReduction(img_gray, label):height, width = img_gray.shapefor x in range(height):for y in range(width):cnt = 0# 白色的點不用管if img_gray[x, y] == 1:continueelse:try:if img_gray[x-1, y-1] == 0:cnt += 1except:passtry:if img_gray[x-1, y] == 0:cnt += 1except:passtry:if img_gray[x-1, y+1] == 0:cnt += 1except:passtry:if img_gray[x, y-1] == 0:cnt += 1except:passtry:if img_gray[x, y+1] == 0:cnt += 1except:passtry:if img_gray[x+1, y-1] == 0:cnt += 1except:passtry:if img_gray[x+1, y] == 0:cnt += 1except:passtry:if img_gray[x+1, y+1] == 0:cnt += 1except:passif cnt < 4: # 周圍少于4點就算是噪點img_gray[x, y] = 1plt.figure('')plt.imshow(img_gray, cmap='gray')plt.axis('off')# plt.show()plt.savefig(''.join(['clean_captcha_img/', label, '.png']))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.mkdir(''.join(['cut_number/', str(i)]))def img_2_clean():captchas = os.listdir(''.join(['captcha_images/']))for captcha in captchas:label = captcha.split('.')[0]img_path = ''.join(['captcha_images/', captcha])# 二值化im = binarizaion(img_path)# 降噪noiseReduction(im, label)def clean_to_cut():captchas = os.listdir(''.join(['clean_captcha_img/']))for captcha in captchas:label = captcha.split('.')[0]cutImg(label)if __name__ == '__main__':img_2_clean()create_dir()clean_to_cut()lee = os.listdir('captcha_images/')for name in lee:lable = name.split('.')[0]path = 'captcha_images/'+namepic = binarizaion(path)noiseReduction(pic,lable)

總結

以上是生活随笔為你收集整理的项目-验证码识别的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。