Code for generating synthetic text images as described in "Synthetic Data for Text Localisation in Natural Images", Ankush Gupta, Andrea Vedaldi, Andrew Zisserman, CVPR 2016.
PyTorch implementation for Score-Based Generative Modeling through Stochastic Differential Equations (ICLR 2021, Oral).
Key parameters and specifications
Key parameters and specifications
Parameter
Value
Language
Python
Category
Model Development
Subcategory
Dataset engineering
Keywords
Data processing, OCR
Stars
2,145
Forks
622
Contributors
3
Created date
2016-09-11
Updated date
2026-10-13
Stars in 1 day
0
Stars in 7 days
-1
Rank
8,926
Previous rank
8,984
Rank change
58
7-day stars rank
16,943
Previous 7-day stars rank
16,941
7-day stars rank change
-2
Total stars rank
5,993
Previous total stars rank
5,987
Total stars rank change
-6
Country
UK
README summary
SynthText Code for generating synthetic text images as described in "Synthetic Data for Text Localisation in Natural Images", Ankush Gupta, Andrea Vedaldi, Andrew Zisserman, CVPR 2016. **Synthetic Scene-Text Image Samples** The code in the branch is for Python2. The main dependencies are: Generating samples where, points to the directory included in the data torrent. Specifying this is optional, and if not specified, the script will automatically download and extract the same data file (~24 M). h5**: This is a
sample h5 file which contains a set of 5 images along with their depth and segmentation information. Note, this is just given as an example; you are encouraged to add more images (along with their depth and segmentation information) to this database for your own use. **fonts**: three sample fonts (add more fonts to this folder and then update with their paths). **newsgroup**: Text-source (from the News Group dataset). This can be subsituted with any text file. Look inside
to see how the text inside this file is used by the renderer. cp**: Color-model (foreground/background text color model), learnt from the IIIT-5K word dataset. **models**: Other cPickle files (**char\_freq. cp**: frequency of each character in the text dataset; **font\_px2pt. cp**: conversion from pt to px for various fonts: If you add a new font, make sure that the corresponding model is present in this file, if not you can add it by adapting ). This
script will generate random scene-text image samples and store them in an h5 file in . If the option is specified, the generated output will be visualized as the script is being run; omit the option to turn-off the visualizations. If you want to visualize the results stored in later, run: Pre-generated Dataset A dataset with approximately 800000 synthetic scene-text images generated with this code can be found in the file in the torrent here; dataset detais
/description in file in the same torrent. Adding New Images Segmentation and depth-maps are required to use new images as background. Sample scripts for obtaining these are available here. MATLAB script to regress a depth mask for a given RGB image; uses the network of Liu etal. and for getting segmentation masks using gPb-UCM. Pre-processed Background Images The 8,000 background images used in the paper, along with their segmentation and depth masks, are included in the
same torrent as the pre-generated dataset under the directory. Note: We do not own the copyright to these images. Generating Samples with Text in non-Latin (English) Scripts @JarveeLee has modified the pipeline for generating samples with Chinese text here. @adavoudi has modified it for arabic/persian script, which flows from right-to-left here. @MichalBusta has adapted it for a number of languages (e. Bangla, Arabic, Chinese, Japanese, Korean) here. @gachiemchiep has adapted for Japanese here. @gungui98 has
adapted for Vietnamese here. @youngkyung has adapted for Korean here. @kotomiDu has developed an interactive UI for generating images with
Frequently asked questions
How many stars and forks are recorded?
ankush-me/SynthText has 2,145 stars and 622 forks.
What is the repository rank?
ankush-me/SynthText is ranked 8,926.
What language and category are recorded?
ankush-me/SynthText has 2,145 stars, uses Python and belongs to Model Development.
Which repository is closest in rank?
ankush-me/SynthText is compared with facebookresearch/SparseConvNet, ranked 8,928 with 2,145 stars.
where, --datadir points to the renderer_data directory included in the
data torrent.
Specifying this datadir is optional, and if not specified, the script will
automatically download and extract the same renderer.tar.gz data file (~24 M).
This data file includes:
sample.h5: This is a sample h5 file which contains a set of 5 images along with their depth and segmentation information. Note, this is just given as an example; you are encouraged to add more images (along with their depth and segmentation information) to this database for your own use.
fonts: three sample fonts (add more fonts to this folder and then update fonts/fontlist.txt with their paths).
newsgroup: Text-source (from the News Group dataset). This can be subsituted with any text file. Look inside text_utils.py to see how the text inside this file is used by the renderer.
models/colors_new.cp: Color-model (foreground/background text color model), learnt from the IIIT-5K word dataset.
models: Other cPickle files (char_freq.cp: frequency of each character in the text dataset; font_px2pt.cp: conversion from pt to px for various fonts: If you add a new font, make sure that the corresponding model is present in this file, if not you can add it by adapting invert_font_size.py).
This script will generate random scene-text image samples and store them in an h5 file in results/SynthText.h5. If the --viz option is specified, the generated output will be visualized as the script is being run; omit the --viz option to turn-off the visualizations. If you want to visualize the results stored in results/SynthText.h5 later, run:
python visualize_results.py
Pre-generated Dataset
A dataset with approximately 800000 synthetic scene-text images generated with this code can be found in the SynthText.zip file in the torrent here; dataset detais/description in readme.txt file in the same torrent.
Adding New Images
Segmentation and depth-maps are required to use new images as background. Sample scripts for obtaining these are available here.
predict_depth.m MATLAB script to regress a depth mask for a given RGB image; uses the network of Liu etal. However, more recent works (e.g., this) might give better results.
run_ucm.m and floodFill.py for getting segmentation masks using gPb-UCM.
For an explanation of the fields in sample.h5 (e.g.: seg,area,label), please check this comment.
Pre-processed Background Images
The 8,000 background images used in the paper, along with their
segmentation and depth masks, are included in the same
torrent
as the pre-generated dataset under the bg_data directory. The files are:
filenames
description
imnames.cp
names of images which do not contain background text
