Skip to main content

LUP Student Papers

LUND UNIVERSITY LIBRARIES

On-line Handwritten Signature Verification using Machine Learning Techniques with a Deep Learning Approach

Drott, Beatrice LU and Hassan-Reza, Thomas LU (2015) In Master's Theses in Mathematical Sciences FMA820 20151
Mathematics (Faculty of Engineering)
Abstract
The problem to be solved in this project is to distinguish two signatures from each other, with help of machine learning techniques. The main technique used is the comparison between two signatures and classifying if they are written by the same person (match) or not (no-match). The binary classication problem is then tackled with a few alternatives to better understand it. First by a simple engineered feature, then by the machine learning techniques as logistic regression, multi-layer perceptron and nally a deep learning approach with a convolutional neural network.
The evaluation method for the dierent algorithms was a plot of true positive rate (sensitivity) versus false positive rate (fall-out). The results of the alternative... (More)
The problem to be solved in this project is to distinguish two signatures from each other, with help of machine learning techniques. The main technique used is the comparison between two signatures and classifying if they are written by the same person (match) or not (no-match). The binary classication problem is then tackled with a few alternatives to better understand it. First by a simple engineered feature, then by the machine learning techniques as logistic regression, multi-layer perceptron and nally a deep learning approach with a convolutional neural network.
The evaluation method for the dierent algorithms was a plot of true positive rate (sensitivity) versus false positive rate (fall-out). The results of the alternative algorithms gave a dierent understanding of the problem. The engineered feature performed unexpectedly well. The logistic regression and multi-layer perceptron performed similarly. The main results from the nal model, which was a max-pooling, convolutional neural network, were a true positive rate of 96.7 % and a false positive rate of 0.6 %.
The deep learning approach on the signature verication problem shows
promising results but there is still room for improvement. (Less)
Please use this url to cite or link to this publication:
author
Drott, Beatrice LU and Hassan-Reza, Thomas LU
supervisor
organization
course
FMA820 20151
year
type
H2 - Master's Degree (Two Years)
subject
keywords
Deep Learning, Convolutional Neural Networks, Signature Verification, On-line Handwritten Signatures, CNN, Biometric Recognition, Machine Learning, Supervised Learning, Logistic Regression, Multi-layer Perceptron, Artifical Neural Networks
publication/series
Master's Theses in Mathematical Sciences
report number
LUTFMA-3282-2015
ISSN
1404-6342
other publication id
2015:E40
language
English
id
8055778
date added to LUP
2015-11-11 13:17:00
date last changed
2015-11-11 13:17:00
@misc{8055778,
  abstract     = {{The problem to be solved in this project is to distinguish two signatures from each other, with help of machine learning techniques. The main technique used is the comparison between two signatures and classifying if they are written by the same person (match) or not (no-match). The binary classication problem is then tackled with a few alternatives to better understand it. First by a simple engineered feature, then by the machine learning techniques as logistic regression, multi-layer perceptron and nally a deep learning approach with a convolutional neural network.
The evaluation method for the dierent algorithms was a plot of true positive rate (sensitivity) versus false positive rate (fall-out). The results of the alternative algorithms gave a dierent understanding of the problem. The engineered feature performed unexpectedly well. The logistic regression and multi-layer perceptron performed similarly. The main results from the nal model, which was a max-pooling, convolutional neural network, were a true positive rate of 96.7 % and a false positive rate of 0.6 %.
The deep learning approach on the signature verication problem shows
promising results but there is still room for improvement.}},
  author       = {{Drott, Beatrice and Hassan-Reza, Thomas}},
  issn         = {{1404-6342}},
  language     = {{eng}},
  note         = {{Student Paper}},
  series       = {{Master's Theses in Mathematical Sciences}},
  title        = {{On-line Handwritten Signature Verification using Machine Learning Techniques with a Deep Learning Approach}},
  year         = {{2015}},
}