keras-ocr实例测试

keras-ocr

文档地址

---

参考文章

一篇入门深度学习OCR：数据集和算法合集

---

错误集合

1. 加载Keras保存的模型时，“ AttributeError：‘str’对象没有属性’decode’”？

pip install ‘numpy1.19’ --force-reinstall 重装库版本
pip install 'h5py2.10.0’ --force-reinstall

2. Win10 conda环境，OSError: [WinError 126] 找不到指定的模块 ·

code example

import matplotlib.pyplot as plt
import keras_ocr

# keras-ocr will automatically download pretrained
# weights for the detector and recognizer.
pipeline = keras_ocr.pipeline.Pipeline()

# Get a set of three example images
# 要一批识别默认的三张图，大概需要预留8g内存，这里只贴两张
images = [
    keras_ocr.tools.read(url) for url in [
        # 'https://upload.wikimedia.org/wikipedia/commons/b/bd/Army_Reserves_Recruitment_Banner_MOD_45156284.jpg',
        'http://5b0988e595225.cdn.sohucs.com/images/20170905/44ecb27c4e5349e28abcbff8f3a6d4d2.jpeg',
        'https://upload.wikimedia.org/wikipedia/commons/b/b4/EUBanana-500x112.jpg'
    ]
]
# Each list of predictions in prediction_groups is a list of
# (word, box) tuples.
prediction_groups = pipeline.recognize(images)

# Plot the predictions
fig, axs = plt.subplots(nrows=len(images), figsize=(20, 20))
for ax, image, predictions in zip(axs, images, prediction_groups):
    keras_ocr.tools.drawAnnotations(image=image, predictions=predictions, ax=ax)
# keras_ocr.tools.drawAnnotations(image=images[-1], predictions=prediction_groups[-1], ax=axs)

plt.show()

---

效果图