Packaged, Pytorch-based, easy to use, cross-platform version of the CRAFT text detector

Related tags

Computer Vision python windows macos linux workflow ocr computer-vision deep-learning neural-network anaconda text craft pypi actions pytorch vision document text-detection
Overview

CRAFT: Character-Region Awareness For Text detection

Downloads PyPI version Conda version CI

Packaged, Pytorch-based, easy to use, cross-platform version of the CRAFT text detector | Paper |

Overview

PyTorch implementation for CRAFT text detector that effectively detect text area by exploring each character region and affinity between characters. The bounding box of texts are obtained by simply finding minimum bounding rectangles on binary map after thresholding character region and affinity scores.

teaser

Getting started

Installation

  • Install using conda for Linux, Mac and Windows (preferred):
conda install -c fcakyon craft-text-detector
  • Install using pip for Linux and Mac:
pip install craft-text-detector

Basic Usage

# import Craft class
from craft_text_detector import Craft

# set image path and export folder directory
image_path = 'figures/idcard.png'
output_dir = 'outputs/'

# create a craft instance
craft = Craft(output_dir=output_dir, crop_type="poly", cuda=False)

# apply craft text detection and export detected regions to output directory
prediction_result = craft.detect_text(image_path)

# unload models from ram/gpu
craft.unload_craftnet_model()
craft.unload_refinenet_model()

Advanced Usage

# import craft functions
from craft_text_detector import (
    read_image,
    load_craftnet_model,
    load_refinenet_model,
    get_prediction,
    export_detected_regions,
    export_extra_results,
    empty_cuda_cache
)

# set image path and export folder directory
image_path = 'figures/idcard.png'
output_dir = 'outputs/'

# read image
image = read_image(image_path)

# load models
refine_net = load_refinenet_model(cuda=True)
craft_net = load_craftnet_model(cuda=True)

# perform prediction
prediction_result = get_prediction(
    image=image,
    craft_net=craft_net,
    refine_net=refine_net,
    text_threshold=0.7,
    link_threshold=0.4,
    low_text=0.4,
    cuda=True,
    long_size=1280
)

# export detected text regions
exported_file_paths = export_detected_regions(
    image_path=image_path,
    image=image,
    regions=prediction_result["boxes"],
    output_dir=output_dir,
    rectify=True
)

# export heatmap, detection points, box visualization
export_extra_results(
    image_path=image_path,
    image=image,
    regions=prediction_result["boxes"],
    heatmaps=prediction_result["heatmaps"],
    output_dir=output_dir
)

# unload models from gpu
empty_cuda_cache()
You might also like...
TextBoxes++: A Single-Shot Oriented Scene Text Detector

TextBoxes++: A Single-Shot Oriented Scene Text Detector Introduction This is an application for scene text detection (TextBoxes++) and recognition (CR

Minghui Liao 930 Jan 4, 2023
TextBoxes: A Fast Text Detector with a Single Deep Neural Network https://github.com/MhLiao/TextBoxes 基于SSD改进的文本检测算法，textBoxes_note记录了之前整理的笔记。

TextBoxes: A Fast Text Detector with a Single Deep Neural Network Introduction This paper presents an end-to-end trainable fast scene text detector, n

zhangjing1 24 Apr 28, 2022
Open Source research tool to search, browse, analyze and explore large document collections by Semantic Search Engine and Open Source Text Mining & Text Analytics platform (Integrates ETL for document processing, OCR for images & PDF, named entity recognition for persons, organizations & locations, metadata management by thesaurus & ontologies, search user interface & search apps for fulltext search, faceted search & knowledge graph)

Open Semantic Search https://opensemanticsearch.org Integrated search server, ETL framework for document processing (crawling, text extraction, text a

Open Semantic Search 684 Jan 6, 2023
Use Convolutional Recurrent Neural Network to recognize the Handwritten line text image without pre segmentation into words or characters. Use CTC loss Function to train.
Use Convolutional Recurrent Neural Network to recognize the Handwritten line text image without pre segmentation into words or characters. Use CTC loss Function to train.

Handwritten Line Text Recognition using Deep Learning with Tensorflow Description Use Convolutional Recurrent Neural Network to recognize the Handwrit

sushant097 224 Jan 7, 2023
Code related to "Have Your Text and Use It Too! End-to-End Neural Data-to-Text Generation with Semantic Fidelity" paper

DataTuner You have just found the DataTuner. This repository provides tools for fine-tuning language models for a task. See LICENSE.txt for license de

null 81 Jan 1, 2023
This can be use to convert text in a file to handwritten text.

TextToHandwriting This can be used to convert text to handwriting. Clone this project or download the code. Run TextToImage.py give the filename of th

Ashutosh Mahapatra 2 Feb 6, 2022
python ocr using tesseract/ with EAST opencv detector

pytextractor python ocr using tesseract/ with EAST opencv text detector Uses the EAST opencv detector defined here with pytesseract to extract text(de

Danny Crasto 38 Dec 5, 2022
Augmenting Anchors by the Detector Itself
Augmenting Anchors by the Detector Itself

Augmenting Anchors by the Detector Itself Introduction It is difficult to determine the scale and aspect ratio of anchors for anchor-based object dete

null 4 Nov 6, 2022
Motion detector, Full body detection, Upper body detection, Cat face detection, Smile detection, Face detection (haar cascade), Silverware detection, Face detection (lbp), and Sending email notifications
Motion detector, Full body detection, Upper body detection, Cat face detection, Smile detection, Face detection (haar cascade), Silverware detection, Face detection (lbp), and Sending email notifications

Security camera running OpenCV for object and motion detection. The camera will send email with image of any objects it detects. It also runs a server that provides web interface with live stream video.

Peace 10 Jun 30, 2021
Comments
  • Add more options for detect_text method

    Add more options for detect_text method

    Hi, sometime I don't want detect_text from file, I want detect_text directly from image in ndarray format, that will save more cost of I/O time. So I contribute this. Thanks for your work

    opened by ducviet00 2
  • Enable package to load model from local path

    Enable package to load model from local path

    When using the pypi package it should be allowed to use a model from a local path, because loading it from a remote location removes the control over what model is currently used. And might also result in pull limits being reached.

    enhancement 
    opened by TanjaBayer 1
  • Fix #8 - Fixing cuda issues in basic usage text detection

    Fix #8 - Fixing cuda issues in basic usage text detection

    Fixing issue #8

    In this quick-fix I referenced craft_net as a global variable. If this is not an acceptable workaround, then consider reorganizing the structure of the code.

    Have a nice day :)

    opened by gaborpelesz 1
  • accept customized weights path when loading models

    accept customized weights path when loading models

    path for the weight file can be specified by:

    load_craftnet_model(weight_path="path/to/weight")

    load_refinenet_model(weight_path="path/to/weight")
    opened by fcakyon 0
Releases(0.4.3)

  • 0.4.3(May 9, 2022)

    What's Changed

    • Enable package to load model from local path by @TanjaBayer in https://github.com/fcakyon/craft-text-detector/pull/53

    New Contributors

    • @TanjaBayer made their first contribution in https://github.com/fcakyon/craft-text-detector/pull/53

    Full Changelog: https://github.com/fcakyon/craft-text-detector/compare/0.4.2...0.4.3

    Source code(tar.gz)
    Source code(zip)

  • 0.4.2(Jan 6, 2022)

    What's Changed

    • fix opencv version by @fcakyon in https://github.com/fcakyon/craft-text-detector/pull/48

    Full Changelog: https://github.com/fcakyon/craft-text-detector/compare/0.4.1...0.4.2

    Source code(tar.gz)
    Source code(zip)

  • 0.4.1(Dec 20, 2021)

    What's Changed

    • fix crop export by @fcakyon in https://github.com/fcakyon/craft-text-detector/pull/45

    Full Changelog: https://github.com/fcakyon/craft-text-detector/compare/0.4.0...0.4.1

    Source code(tar.gz)
    Source code(zip)

  • 0.4.0(Jul 30, 2021)

  • 0.3.5(May 12, 2021)

  • 0.3.4(Apr 7, 2021)

    • add support for PIL and numpy images in addition to filepath. https://github.com/fcakyon/craft-text-detector/pull/28
    from PIL import Image
import numpy

# can be filepath, PIL image or numpy array
image = 'figures/idcard.png' 
image = Image.open("figures/idcard.png")
image = numpy.array(Image.open("figures/idcard.png"))

# apply craft text detection
prediction_result = craft.detect_text(image)
    Source code(tar.gz)
    Source code(zip)

  • 0.3.3(Mar 2, 2021)

  • 0.3.2(Mar 2, 2021)

    path for the weight file can be specified by:

    load_craftnet_model(weight_path="path/to/weight")

    load_refinenet_model(weight_path="path/to/weight")
    Source code(tar.gz)
    Source code(zip)

  • v0.3.1(May 14, 2020)

  • v0.3.0(May 14, 2020)

    • updated basic usage for better device handling, now Craft instance should be created before calling detect_text:
    # import Craft class
from craft_text_detector import Craft

# set image path and export folder directory
image_path = 'figures/idcard.png'
output_dir = 'outputs/'

# create a craft instance
craft = Craft(output_dir=output_dir, crop_type="poly", cuda=False)

# apply craft text detection and export detected regions to output directory
prediction_result = craft.detect_text(image_path)

# unload models from ram/gpu
craft.unload_craftnet_model()
craft.unload_refinenet_model()
    • some internal naming and styling changes
    Source code(tar.gz)
    Source code(zip)

  • v0.2.1(May 10, 2020)

  • v0.2.0a(Apr 22, 2020)

  • v0.2.0(Apr 22, 2020)

Owner
Senior Machine Learning Engineer, METU & Bilkent alum.
null
GitHub
Official implementation of Character Region Awareness for Text Detection (CRAFT)

CRAFT: Character-Region Awareness For Text detection Official Pytorch implementation of CRAFT text detector | Paper | Pretrained Model | Supplementary

Clova AI Research 2.5k Jan 3, 2023
This is a implementation of CRAFT OCR method

This is a implementation of CRAFT OCR method

Esaka 0 Nov 1, 2021
This is a c++ project deploying a deep scene text reading pipeline with tensorflow. It reads text from natural scene images. It uses frozen tensorflow graphs. The detector detect scene text locations. The recognizer reads word from each detected bounding box.

DeepSceneTextReader This is a c++ project deploying a deep scene text reading pipeline. It reads text from natural scene images. Prerequsites The proj

Dafang He 49 Sep 10, 2022
Genalog is an open source, cross-platform python package allowing generation of synthetic document images with custom degradations and text alignment capabilities.

Genalog is an open source, cross-platform python package allowing generation of synthetic document images with custom degradations and text alignment capabilities.

Microsoft 235 Dec 22, 2022
This is a pytorch re-implementation of EAST: An Efficient and Accurate Scene Text Detector.

EAST: An Efficient and Accurate Scene Text Detector Description: This version will be updated soon, please pay attention to this work. The motivation

Dejia Song 544 Dec 20, 2022
PyTorch Re-Implementation of EAST: An Efficient and Accurate Scene Text Detector

Description This is a PyTorch Re-Implementation of EAST: An Efficient and Accurate Scene Text Detector. Only RBOX part is implemented. Using dice loss

null 365 Dec 20, 2022
Implement 'Single Shot Text Detector with Regional Attention, ICCV 2017 Spotlight'

SSTDNet Implement 'Single Shot Text Detector with Regional Attention, ICCV 2017 Spotlight' using pytorch. This code is work for general object detecti

HotaekHan 84 Jan 5, 2022
Single Shot Text Detector with Regional Attention

Single Shot Text Detector with Regional Attention Introduction SSTD is initially described in our ICCV 2017 spotlight paper. A third-party implementat

Pan He 215 Dec 7, 2022
A tensorflow implementation of EAST text detector

EAST: An Efficient and Accurate Scene Text Detector Introduction This is a tensorflow re-implementation of EAST: An Efficient and Accurate Scene Text

null 2.9k Jan 2, 2023
Implementation of EAST scene text detector in Keras

EAST: An Efficient and Accurate Scene Text Detector This is a Keras implementation of EAST based on a Tensorflow implementation made by argman. The or

Jan Zdenek 208 Nov 15, 2022