def main(fn):
# 读取并预处理验证码
img = cv2.imread(fn, cv2.IMREAD_GRAYSCALE)
text = pretreatment.get_text(img)
imgs = pretreatment.get_imgs(img)
text = text / 255.0
h, w = text.shape
text.shape = (1, h, w, 1)
# 识别文字
model = models.load_model('model.h5')
label = model.predict(text)
label = label.argmax()
print(label)
# 加载图片分类器
data = np.load('images.npz')
images, labels = data['images'], data['labels']
labels = labels.argmax(axis=1)
for pos, img in enumerate(imgs):
try:
img.dtype = np.uint64
img = img[0]
idx = list(images).index(img)
label = labels[idx]
print(pos // 4, pos % 4, label)
except:
print('unknown')
def get_text(img, offset=0):
text = pretreatment.get_text(img, offset)
text = cv2.cvtColor(text, cv2.COLOR_BGR2GRAY)
text = text / 255.0
h, w = text.shape
text.shape = (1, h, w, 1)
return text
def main(fn):
# 读取并预处理验证码
img = cv2.imread(fn)
text = pretreatment.get_text(img)
text = cv2.cvtColor(text, cv2.COLOR_BGR2GRAY)
imgs = np.array(list(pretreatment._get_imgs(img)))
imgs = imgs / 255.0
text = text / 255.0
h, w = text.shape
text.shape = (1, h, w, 1)
_, h, w, _ = imgs.shape
imgs.shape = (-1, h, w, 3)
# 识别文字
model = models.load_model('model.h5')
label = model.predict(text)
label = label.argmax()
print(label)
# 加载图片分类器
model = models.load_model('12306.image.model.h5')
labels = model.predict(imgs)
labels = labels.argmax(axis=1)
for pos, label in enumerate(labels):
print(pos // 4, pos % 4, label)
def get_text(self, img):
img_array = np.array(img)
text = pretreatment.get_text(img_array)
text = cv2.cvtColor(text, cv2.COLOR_BGR2GRAY)
text = text / 255.0
h, w = text.shape
text.shape = (1, h, w, 1)
return text
def get_text(img, offset=0):
"""
获取图片文本信息
:param img: 验证码图片句柄，cv2.imread返回值
:param offset:
:return: 图片处理后的文本信息
"""
text = pretreatment.get_text(img, offset)
text = cv2.cvtColor(text, cv2.COLOR_BGR2GRAY)
text = text / 255.0
h, w = text.shape
text.shape = (1, h, w, 1)
return text
def verify(self, i):
verify_titles = [
'打字机', '调色板', '跑步机', '毛线', '老虎', '安全帽', '沙包', '盘子', '本子', '药片',
'双面胶', '龙舟', '红酒', '拖把', '卷尺', '海苔', '红豆', '黑板', '热水袋', '烛台', '钟表',
'路灯', '沙拉', '海报', '公交卡', '樱桃', '创可贴', '牌坊', '苍蝇拍', '高压锅', '电线',
'网球拍', '海鸥', '风铃', '订书机', '冰箱', '话梅', '排风机', '锅铲', '绿豆', '航母',
'电子秤', '红枣', '金字塔', '鞭炮', '菠萝', '开瓶器', '电饭煲', '仪表盘', '棉棒', '篮球',
'狮子', '蚂蚁', '蜡烛', '茶盅', '印章', '茶几', '啤酒', '档案袋', '挂钟', '刺绣', '铃铛',
'护腕', '手掌印', '锦旗', '文具盒', '辣椒酱', '耳塞', '中国结', '蜥蜴', '剪纸', '漏斗',
'锣', '蒸笼', '珊瑚', '雨靴', '薯条', '蜜蜂', '日历', '口哨'
]
img = Image.open("../pic/verify{}.png".format(i))
text = self.get_text(img)
imgs = np.array(list(pretreatment._get_imgs(img)))
imgs = preprocess_input(imgs)
text_list = []
self.LoadTextModel()
label = self.textModel.predict(text)
label = label.argmax()
text = verify_titles[label]
text_list.append(text)
print("题目是{}".format(text))
# 获取下一个词
# 根据第一个词的长度来定位第二个词的位置
if len(text) == 1:
offset = 27
elif len(text) == 2:
offset = 47
else:
offset = 60
text = pretreatment.get_text(img, offset=offset)
if text.mean() < 0.95:
label = self.textModel.predict(text)
label = label.argmax()
text = verify_titles[label]
text_list.append(text)
print("题目是{}".format(text_list))
# 加载图片分类器
self.LoadImgModel()
labels = self.imgModel.predict(imgs)
labels = labels.argmax(axis=1)
results = []
for pos, label in enumerate(labels):
l = verify_titles[label]
print(pos + 1, l)
if l in text_list:
results.append(str(pos + 1))
print(results)
return results
import os
import cv2
import numpy as np
import pretreatment
path = 'imgs'
texts = []
images = []
i = 0
for fn in os.listdir(path):
i += 1
fn = os.path.join(path, fn)
im = cv2.imread(fn)
text = pretreatment.get_text(im)
texts.append(text)
images.append(list(pretreatment._get_imgs(im)))
if i >= 2000:
break
np.savez_compressed('dataset.npz', texts=texts, images=images)
# coding: utf-8
import sys
import cv2
import numpy as np
from keras import models
import pretreatment
from mlearn_for_image import preprocess_input
def get_text(img, offset=0):
text = pretreatment.get_text(img, offset)
text = cv2.cvtColor(text, cv2.COLOR_BGR2GRAY)
text = text / 255.0
h, w = text.shape
text.shape = (1, h, w, 1)
return text
def main(fn):
# 读取并预处理验证码
img = cv2.imread(fn)
text = get_text(img)
imgs = np.array(list(pretreatment._get_imgs(img)))
imgs = preprocess_input(imgs)
# 识别文字
model = models.load_model('model.v2.0.h5')
label = model.predict(text)
label = label.argmax()
