Skip to main content

A packaged and flexible version of the CRAFT text detector and Keras CRNN recognition model.

Reason this release was yanked:

The URLs for weights have changed. Please upgrade.

Project description

keras-ocr

This is a slightly polished and packaged version of the Keras CRNN implementation and the published CRAFT text detection model. It provides a high level API for training a text detection and OCR pipeline.

Please see the documentation for more examples, including for training a custom model.

Getting Started

Installation

# To install from master
pip install git+https://github.com/faustomorales/keras-ocr.git#egg=keras-ocr

# To install from PyPi
pip install keras-ocr

Using

Using pretrained text detection and recognition models

The package ships with an easy-to-use implementation of the CRAFT text detection model from this repository and the CRNN recognition model from this repository.

import matplotlib.pyplot as plt

import keras_ocr

# keras-ocr will automatically download pretrained
# weights for the detector and recognizer.
detector = keras_ocr.detection.Detector()
recognizer = keras_ocr.recognition.Recognizer()

image = keras_ocr.tools.read('tests/test_image.jpg')

# Boxes will be an Nx4x2 array of box quadrangles
# where N is the number of detected text boxes.
# Predictions is a list of (string, box) tuples.
boxes = detector.detect(images=[image])[0]
predictions = recognizer.recognize_from_boxes(image=image, boxes=boxes)

# Plot the results.
fig, (ax1, ax2) = plt.subplots(ncols=2, figsize=(10, 10))
canvas = keras_ocr.detection.drawBoxes(image, boxes)
ax1.imshow(image)
ax2.imshow(canvas)

for text, box in predictions:
    ax2.annotate(s=text, xy=box[0], xytext=box[0] - 50, arrowprops={'arrowstyle': '->'})

example of labeled image

Project details


Release history Release notifications | RSS feed

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

keras-ocr-0.4.1.tar.gz (146.0 kB view hashes)

Uploaded Source

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page