Program to extract signatures from documents.

Overview

Extracting Signatures from Bank Checks

Introduction

Ahmed et al. [1] suggest a connected components-based method for segmenting signatures in document images. For this purpose, they train and evaluate their models on Tobacco-800 documents dataset to extract patch-level signatures.

In this project, we have taken their proposal and modified it to work specifically for bank checks, and be able to segment signatures on a stroke level instead of patch level. Both these are inherently more difficult problems.

Bank checks have complex backgrounds which are not known beforehand. This was not the case in Tobacco-800 dataset where the documents have a simple white background. Similarly, extracting stroke-level position of the signature is again a more difficult task compared to patch level location.

Demo

You can watch a demo of the results in the following Youtube video
Demo Video

Datasets

One reason why [1] worked on patch-level was a lack of publicly available datasets with groundtruth at stroke-level. In this project, we have created our own dataset of bank checks with stroke level groundtruth available as binary segmentation masks. We use this dataset for testing.

We divide our training data into two classes: signatures and non-signature. For non-signature class, we took 64 documents from Tobacco-800 [3, 4] to manually generate new images which which didn't contain any signatures or handwritten text. Some of these documents contained logos, as well. For the signature class, we combined all images from the UTSig signature database [2], which contains 8280 Persian language signatures.

Installation

Clone the project and cd to project directory. Then, execute the following commands once to set-up your environment

python3 -m venv venv/
source venv/bin/activate
pip install -r requirements.txt

Then you can run the GUI app with python3 src/extract_gui.py.

The repository comes with trained models in the models/ folder. To train a new model with your own data, look at the train_test.py script.

References

  1. Ahmed, S., Malik, M. I., Liwicki, M., & Dengel, A. (2012, September). Signature segmentation from document images. In 2012 International Conference on Frontiers in Handwriting Recognition (pp. 425-429). IEEE.

  2. Soleimani, A., Fouladi, K., & Araabi, B. N. (2016). UTSig: A Persian offline signature dataset. IET Biometrics, 6(1), 1-8.

  3. Zhu, G., & Doermann, D. (2007, September). Automatic document logo detection. In Ninth International Conference on Document Analysis and Recognition (ICDAR 2007) (Vol. 2, pp. 864-868). IEEE.

  4. Zhu, G., Zheng, Y., Doermann, D., & Jaeger, S. (2007, June). Multi-scale structural saliency for signature detection. In 2007 IEEE Conference on Computer Vision and Pattern Recognition (pp. 1-8). IEEE.

Owner
Muhammad Saif Ullah Khan
Mobile developer and ML engineer.
Muhammad Saif Ullah Khan
Run functions in parallel easily, with their results typed correctly!

typesafe_parmap pip install pip install typesafe-parmap Run functions in parallel safely with typesafe parmap! GitHub: https://github.com/thejaminato

James Chua 3 Nov 06, 2021
Airspy-Utils is a small software collection to help with firmware related operations on Airspy HF+ devices.

Airspy-Utils Airspy-Utils is a small software collection to help with firmware related operations on Airspy HF+ devices on Linux (and other free syste

Dhiru Kholia 11 Oct 04, 2022
Simple Python tool that generates a pseudo-random password with numbers, letters, and special characters in accordance with password policy best practices.

Simple Python tool that generates a pseudo-random password with numbers, letters, and special characters in accordance with password policy best practices.

Joe Helle 7 Mar 25, 2022
Automatically Generate Rulesets for IIS for Intelligent HTTP/S C2 Redirection

Automatically Generate Rulesets for IIS for Intelligent HTTP/S C2 Redirection This project converts a Cobalt Strike profile to a functional web.config

Jesse 99 Dec 13, 2022
Extract XML from the OS X dictionaries.

Extract XML from the OS X dictionaries.

Joshua Olson 13 Dec 11, 2022
[P]ython [w]rited [B]inary [C]onverter

pwbinaryc [P]ython [w]rited [Binary] [C]onverter You have rights to: Modify the code and use it private (friends are allowed too) Make a page and redi

0 Jun 21, 2022
Software to help automate collecting crowdsourced annotations using Mechanical Turk.

Video Crowdsourcing Software to help automate collecting crowdsourced annotations using Mechanical Turk. The goal of this project is to enable crowdso

Mike Peven 1 Oct 25, 2021
A program will generate a eth key pair that has the public key that starts with a defined amount of 0

ETHAdressGenerator This short program will generate a eth key pair that has the public key that starts with a defined amount of 0 Requirements Python

3 Nov 19, 2021
.bvh to .mcfunction file converter.

bvh-to-mcf .bvh file to .mcfunction converter

Hanmin Kim 28 Nov 21, 2022
A script to check for common mistakes in LaTeX source files of scientific papers.

LaTeX Paper Linter This script checks for common mistakes in LaTeX source files of scientific papers. Usage python3 paperlint.py file.tex [-i/x inc

Michael Schwarz 12 Nov 16, 2022
Simple tool for creating changelogs

Description Simple utility for quickly generating changelogs, assuming your commits are ordered as they should be. This tool will simply log all lates

2 Jan 05, 2022
Dill_tils is a package that has my commonly used functions inside it for ease of use.

DilllonB07 Utilities Dill_tils is a package that has my commonly used functions inside it for ease of use. Installation Anyone can use this package by

Dillon Barnes 2 Dec 05, 2021
A collection of custom scripts for working with Quake assets.

Custom Quake Tools A collection of custom scripts for working with Quake assets. Features Script to list all BSP files in a Quake mod

Jason Brownlee 3 Jul 05, 2022
Simple code to generate a password for your account!

Password-Generator Simple code to generate a password for your account! Password Generator for passwords for your accounts or anything else! This code

DEEM 1 Jun 05, 2022
Abby's Left Hand Modifiers Dictionary

Abby's Left Hand Modifiers Dictionary Design This dictionary is inspired by and

12 Dec 08, 2022
A utility tool to create .env files

A utility tool to create .env files dump-env takes an .env.template file and some optional environmental variables to create a new .env file from thes

wemake.services 89 Dec 08, 2022
Helpful functions for use alongside the rich Python library.

🔧 Rich Tools A python package with helpful functions for use alongside with the rich python library. 󠀠󠀠 The current features are: Convert a Pandas

Avi Perl 14 Oct 14, 2022
A quick random name generator

Random Profile Generator USAGE & CREDITS Any public or priavte demonstrative usage of this project is strictly prohibited, UNLESS WhineyMonkey10 (http

2 May 05, 2022
An online streamlit development platform

streamlit-playground An online streamlit development platform Run, Experiment and Play with streamlit Components Develop full-fledged apps online All

Akshansh Kumar 3 Nov 06, 2021
Simple web index to use bloom filter for Pwned Passwords

pwbloom Simple web index to use bloom filter for Pwned Passwords The index.py runs a simple CGI web service checking passwords with a bloom filter for

Hanno Böck 4 Nov 23, 2021