You are on page 1of 10

IAETSD JOURNAL FOR ADVANCED RESEARCH IN APPLIED SCIENCES ISSN NO: 2394-8442

Comparative Analysis of Online Signature Verification using Hybrid Wavelet


Transform (HWT) -1 and 2 with HMM classifier
1
Manoj Chavan, 2 Ravish R. Singh, 3Vinayak Bharadi
1 Faculty
of Engineering, Pacific Academy of Higher Education and Research University, Udaipur, India,
2 Thakur Educational Trust, Mumbai, India,

3 Information Technology Department, Finolex Academy of Management and Technology, Ratnagiri (MH), India

1 prof.manoj@gmail.com, 2 ravishrsingh@yahoo.com , 3 vinayak.bharadi@famt.ac.in

Abstract—Online handwritten signature contains additional dynamic features such as pressure applied by user, speed
of writing, method of holding the pen etc. along with two dimensional image of the signatures obtained by offline
signatures. The hybrid wavelet transform which are formed by using Kronecker product of two transform, has the ability
to analyse the signal at global as well as local level. Hybrid wavelet transform – 1 and 2 were applied on the first 128
samples of the pressure parameter and first 1- 16 samples of the output were used as feature vector for signature
verification. Using Hidden Markov Model (HMM) based classifier with ergodic model, the performance of the proposed
system was analysed. DHT KEKRE, HAAR KEKRE, HADAMARD KEKRE, KEKRE HADAMARD and KEKRE
128 best performance with FRR and FAR of 0 % with HWT-1. KEKRE 128 offers best performance with FRR & FAR
of 13 % with HWT-2. HWT - 1 offers better performance in terms of FRR – FAR than HWT - 2. HADAMARD HAAR
transform offers best EER of 8 training samples with HWT -1. Orthogonal DCT transform, DCT HADAMARD, DHT
DCT and HAAR HADAMARD transform offers best EER of 4 training samples with HWT -2.

Keywords— HMM, Hybrid Wavelet Transform – 1, Hybrid Wavelet Transform - 2, Online Signature
Verification, FRR, FAR, EER.
I. INTRODUCTION
Any individual can be uniquely identified by using biometric features. [1] These features are of two types, namely,
Physical and behavioural. Handwritten Signatures fall in the category of behavioural features which also include voice,
typing rhythm etc. Signatures have been used for a long time for authenticating an individual as it is very easy to obtain. [2]
As a biometric feature, signatures are of two type, offline and online signatures. Offline signature is a two dimensional
image of the signature, done on the paper whereas the online signature contains additional dynamic features such as
pressure applied by user, speed of writing , method of holding the pen etc. along with two dimensional image of the
signatures. [3] For computerizing the process of signature verification, online signatures offers more advantages than the
offline signatures due to its dynamic features.

II. PROPOSED TECHNIQUE


In general biometric system consist of data acquisition, pre-processing, feature extraction, classification and
performance evaluation. In this system, the user will sign some sample signatures on pressure sensitive writing pads. The
proposed method is as shown fig. 1. Every signature sample will have X-coordinate - scaled cursor position along the x-
axis, Y-coordinate - scaled cursor position along the y-axis, Time stamp - system time at which the event was posted,
Button status - current button status (0 for pen-up and 1 for pen-down), Azimuth - clockwise rotation of cursor about the
z-axis, Altitude - angle upward toward the positive z-axis, Pressure - adjusted state of the normal pressure. We used
signature database provided by The First International Signature Verification Competition (SVC 2004) consisting of 1600
signatures. It has signature samples of 40 users. Every user has 40 signature samples, out of which, 20 are genuine and 20
are skilled forgeries.

VOLUME 4, ISSUE 7, DEC/2017 143 http://iaetsdjaras.org/


IAETSD JOURNAL FOR ADVANCED RESEARCH IN APPLIED SCIENCES ISSN NO: 2394-8442

[4] It is observed that out of the seven features of online signatures, Pressure applied by the tip of the pen on the
pressure sensitive pad has the highest level of variation and has therefore been chosen for the feature vector. Various
orthogonal transforms have been used to analyse the overall signal thereby giving its global properties. Wavelet Transform
can analyse the signal at various resolution level thereby extracting its global as well as local properties. The orthogonal
transforms are used to analyse the global properties of a signal. The hybrid wavelet transform which are formed by using
Kronecker product of two transform, has the ability to analyse the signal at global as well as local level [5].

Fig. 1: Proposed System

III. METHODOLOGY
HWT -1 matrix ‘TXY’ of size (NxN), as shown in Table I, can be formed by the Kronecker product of two orthogonal
transform matrices X and Y respectively, with sizes (a x a) and (b x b), such that N=ab. For HWT – 1, first ‘b’ number of
rows of the HWT matrix are calculated as the product of each element of first row of the orthogonal transform X with
each of the columns of the orthogonal transform Y. For next ‘b’ number of rows of HWT matrix the second row of the
orthogonal transform matrix X is shift rotated after being appended with zeros. Similarly the other rows of HWT matrix
are generated as set of b rows each time for each of the ‘a-1’ rows of orthogonal transform matrix X starting from second
row up to last row. HWT-2 matrix is shown in Table II. First N/2 rows of the matrix are formed by product of each
element of first a/2 rows of the matrix X with each of the columns of the matrix Y. For next ‘b’ number of rows of matrix,
the ‘a/2+1’th row of the orthogonal transform matrix X is shift rotated after being appended with zeros. Next N/2 rows
are generated as set of b rows each time for each of the ‘a/2’ rows of orthogonal transform matrix X starting from
‘a/2+1’th row up to last row. [6] We have used Discrete Cosine transform (DCT), Discrete Hartley transform (DHT),
Discrete Walsh transform (DWT) and Discrete Kekre transform (DKT) to form the Wavelet and HWT-2. [7] The first
128 samples of every signature is used to find hybrid wavelet transform. The first 16 samples and the samples 33 to 64 of
the output are used as feature vector.

Table I
HWT -1 matrix
y11x11 y11x12 … y11x1a y12x11 y12x12 … y12x1a … … y1bx11 y1bx12 … y1bx1a
y21x11 y21x12 … y21x1a y22x12 y22x12 … y22x1a … … y2bx11 y2bx12 … y2bx1a
… … … … … … … … … … … … … …
yb1x11 yb1x12 … yb1x1a yb2x11 yb2x12 … yb2x1a … … ybbx11 ybbx12 … ybbx1a
x21 x22 … x2a 0 0 … 0 … … 0 0 … 0
0 0 0 0 x21 x22 … x2a … … 0 0 … 0
… … … … … … … … … … … … … …
0 0 … 0 0 0 … 0 … … x21 x22 … x2a
x31 x32 … x3a 0 0 … 0 … … 0 0 … 0
0 0 0 x31 x32 … x3a … … 0 0 … 0
… … … … … … … … … … … … … …
0 0 0 0 0 … 0 … … x31 x32 … x3a
… … … … … … … … … … … … … …
… … … … … … … … … … … … … …
xa1 xa2 … xaa 0 0 … 0 … … 0 0 … 0
0 0 … 0 xa1 xa2 … xaa … … 0 0 … 0
… … … … … … … … … … … … … …
0 0 … 0 0 0 … 0 … … xa1 xa2 … xaa

VOLUME 4, ISSUE 7, DEC/2017 144 http://iaetsdjaras.org/


IAETSD JOURNAL FOR ADVANCED RESEARCH IN APPLIED SCIENCES ISSN NO: 2394-8442

Classifiers are trained by using the sample training signatures. After training they are used to verify, the feature of the
test signature with those stored in the database to decide whether the signature is genuine or forged. Various classifiers
used are classifiers based on Dynamic Time warping [8], Neural Networks (NN) [9], Hidden Markov Model (HMM) [10]
[11] and Support Vector Machine (SVM). [12] We have used HMM based classifier. Consider a system which is in a
distinct state (S1, S2, …., SN) at any point of time. In Markov Models the future state is always dependent on the current
state and is independent of past state P (St=j / St-1=i, St-2=k …) = P (St=j / St-1=i). The states and associated transition
probabilities are known to the user. In case of Hidden Markov Model states will not be known but the output which is
dependent on the state, will be known to user. [13]

There are many topologies of HMM such as Left to Right, Ergodic and Ring. Ergodic model as shown in fig 2.

Fig 2: Ergodic model


HMM is represented by the transition probability matrix (A), Observation matrix (B) and initial probability distribution
matrix (π). Various parameters of HMM are as follows: Number of states (N) in the model: In this experiment the number
of states are varied from 2 to 5. As the number of states increase, the time needed for training increases.

Number of observations (M) corresponding to each state: In this experiment the number of observations are varied
from 200 to 750 in the increments of 25. The output of hybrid wavelet transform is a matrix of dimension [1 × 128]. The
matrix elements from 1 to 16 and 33 to 64 are chosen as a feature vector. Feature vectors are scaled into M number of
observations.

VOLUME 4, ISSUE 7, DEC/2017 145 http://iaetsdjaras.org/


IAETSD JOURNAL FOR ADVANCED RESEARCH IN APPLIED SCIENCES ISSN NO: 2394-8442

Initial Probability Distribution (π): πi = P (q1= Si); 1 ≤ i ≤ N. For the Ergodic HMM, the initial probability of the first
state is 1 and the others are 0. This implies that at the beginning, the HMM is always in state 1.

State transition probability (aij): aij = P (St=j / St-1=i ). For the left-to-right HMM, aij=0 when i>j. we are using the
HMM of first order so that aij=0 when j>i+1. Initially, the state transition matrix is generated using the random numbers
such that ; 1 ≤ i ≤ N.

Observation probability (bj): bj (k) = P (Vk at t / qt = Sj); 1 ≤ j ≤ N; 1 ≤ k ≤ M; the probability of generating a symbol
Vk in state j.

We have used statistics and machine learning toolbox of the MATLAB 13. Initially we assumed a randomly generated
transition probability Matrix (A) generated using MATLAB, Observation probability matrix (B) with equal probability for
every symbols and HMM to be in state 1. HMM is trained using hmmtrain for 3 to 20 genuine training signature samples,
number of states from 2 to 5 and symbols from 200 to 750. After HMM is trained, it is used to test 20 genuine and 20
forged signatures of 40 users.

IV. RESULT AND DISCUSSION


Performance of the system will be measured on the basis of False Rejection Ratio (FRR) and False Acceptance Ratio
(FAR). FRR refers to false rejection of genuine signature and FAR refers to false acceptance of forged signature. [14] FRR
will be computed as ratio of the number of signatures detected as forged to the total number of genuine signatures tested.
FAR will be computed as ratio of the number of signatures detected as genuine to the total forged signatures tested.
Testing has been carried out for 40 users and then the average FRR and FAR are calculated. In FRR-FAR plot, the point
where two graphs cross each other is referred as Equal Error Rate (EER). At this point the value of FRR and FAR is
minimum. We choose the EER such that it is the nearest number of training samples such that FRR and FAR are
minimum.

The comparison of HWT-1 and 2 for 1 – 16 bit for DCT combinations is shown in the Table III. Best FRR – FAR:
FRR – FAR should be as low as possible. For HWT - 1, DCT KEKRE offers best performance with FRR 5 % & FAR of
10 %. For HWT - 2, DCT KEKRE offers best performance with FRR 22% & FAR of 31 %. The performance offered by
DCT KEKRE HWT for HWT - 1 is better than HWT - 2. The performance offered by DCT combinations for HWT - 1
is better than HWT - 2. For HWT – 1, the performance offered by DCT KEKRE is better than Orthogonal DCT
transform. For HWT – 2, all combinations of DCT offer better performance than Orthogonal DCT transform.

Fig. 3: FRR – FAR plot

VOLUME 4, ISSUE 7, DEC/2017 146 http://iaetsdjaras.org/


IAETSD JOURNAL FOR ADVANCED RESEARCH IN APPLIED SCIENCES ISSN NO: 2394-8442

Best EER: EER in terms of training samples should be as low as possible. For HWT – 1, DCT HAAR offers best
performance of 11 compared to 15 training samples for Orthogonal DCT transform. For HWT – 2, Orthogonal DCT
transform and DCT HADAMARD offers best performance of 4 training samples compared to all combinations of DCT
HWT. The performance offered by DCT combinations for HWT - 2 is better than HWT - 1.

Best state wise FRR – FAR: FRR – FAR should be as low as possible for the given state from 2 to 5. For HWT - 1,
DCT DHT offers best performance for 2 to 5 states compared to orthogonal DCT transform. For HWT - 2, DCT
KEKRE offers best performance for 2 to 5 states compared to orthogonal DCT transform. The performance offered by
DCT combinations for HWT - 1 is better than HWT - 2.

Best Number of Symbol: It should be as low as possible. Testing was carried out for number of symbols from 200 to
750. It evident that the best performance in terms of FRR – FAR is offered by 300 to 325 symbols for HWT - 1 and 450 –
500 symbols for HWT - 2. The performance offered by DCT combinations for HWT - 1 is better than HWT - 2.

The comparison of HWT-1 and 2 for 1 – 16 bit for DHT combinations is shown in the Table III.

Best FRR – FAR: FRR – FAR should be as low as possible. For HWT - 1, DHT KEKRE offers best performance with
FRR & FAR of 0 %. For HWT - 2, DHT KEKRE offers best performance with FRR & FAR of 24 %. The performance
offered by DHT KEKRE HWT for HWT - 1 is better than HWT - 2. The performance offered by DHT combinations
for HWT - 1 is better than HWT - 2. For HWT – 1, the performance offered by DHT DCT, DHT KEKRE is better than
Orthogonal DHT transform. For HWT – 2, only DHT KEKRE offers better performance than Orthogonal DHT
transform.

VOLUME 4, ISSUE 7, DEC/2017 147 http://iaetsdjaras.org/


IAETSD JOURNAL FOR ADVANCED RESEARCH IN APPLIED SCIENCES ISSN NO: 2394-8442

Best EER: EER in terms of training samples should be as low as possible. For HWT – 1, DHT HADAMARD offers
best performance of 9 training samples compared to 11 training samples for Orthogonal DHT transform. For HWT – 2,
DHT DCT offers best performance of 4 training samples compared to 5 training samples for Orthogonal DHT transform.
The performance offered by DHT combinations for HWT - 2 is better than HWT - 1.

Best state wise FRR – FAR: FRR – FAR should be as low as possible for the given state from 2 to 5. For HWT - 1,
DHT HADAMARD offers best performance for 2 to 5 states compared to orthogonal DHT transform. For HWT - 2,
DHT KEKRE offers best performance for 2 to 5 states compared to orthogonal DHT transform. The performance
offered by DHT combinations for HWT - 2 is better than HWT – 1 for 2 and 5 states. The performance offered by DHT
combinations for HWT - 1 is better than HWT – 2 for 3 and 4 states.

Best Number of Symbol: It should be as low as possible. Testing was carried out for number of symbols from 200 to
750. It evident that the best performance in terms of FRR – FAR is offered by 300 symbols for HWT - 1 and 450 - 500
symbols for HWT - 2. The performance offered by DHT combinations for HWT - 1 is better than HWT - 2.

The comparison of HWT-1 and 2 for 1 – 16 bit for HAAR combinations is shown in the Table IV.

Best FRR – FAR: FAR should be as low as possible. For HWT - 1, HAAR KEKRE offers best performance with FRR
& FAR of 0 %. For HWT - 2, HAAR KEKRE offers best performance with FRR 20 % & FAR of 21 %. The
performance offered by HAAR KEKRE HWT for HWT - 1 is better than HWT - 2. The performance offered by HAAR
combinations for HWT - 1 is better than HWT - 2. For HWT – 1, the performance offered by HAAR KEKRE is better
than Orthogonal HAAR transform. For HWT – 2, HAAR DCT and HAAR KEKRE offers better performance than
Orthogonal HAAR transform.

VOLUME 4, ISSUE 7, DEC/2017 148 http://iaetsdjaras.org/


IAETSD JOURNAL FOR ADVANCED RESEARCH IN APPLIED SCIENCES ISSN NO: 2394-8442

Best EER: EER in terms of training samples should be as low as possible. For HWT – 1, HAAR DCT and HAAR
HADAMARD offers best performance of 12 training samples compared to 14 training samples for Orthogonal HAAR
transform. For HWT – 2, HAAR HADAMARD offers best performance of 4 training samples compared to 6 training
samples for Orthogonal HAAR transform. The performance offered by DHT combinations for HWT - 2 is better than
HWT - 1.

Best state wise FRR – FAR: FRR – FAR should be as low as possible for the given state from 2 to 5. For HWT - 1,
HAAR KEKRE offers best performance for 2 to 5 states. For HWT - 2, HAAR KEKRE offers best performance for 2 to
5 states compared to orthogonal HAAR transform. Performance offered by HAAR combinations for HWT - 1 is better
than HWT - 2.

Best Number of Symbol: It should be as low as possible. Testing was carried out for number of symbols from 200 to
750. It evident that the best performance in terms of FRR – FAR, AAR – ARR, EER is offered by 300 and 550 symbols
for HWT - 1 and 400 – 500 symbols for HWT - 2. The performance offered by HAAR combinations for HWT - 1 is
better than HWT - 2.
Table V
Performance comparison of HWT -1 and 2 for KEKRE

The comparison of HWT-1 and 2 for 1 – 16 bit for HADAMARD combinations is shown in the Table IV.

VOLUME 4, ISSUE 7, DEC/2017 149 http://iaetsdjaras.org/


IAETSD JOURNAL FOR ADVANCED RESEARCH IN APPLIED SCIENCES ISSN NO: 2394-8442

Best FRR – FAR: FAR should be as low as possible. For HWT - 1, HADAMARD KEKRE offers best performance
with FRR & FAR of 0 %. For HWT - 2, HADAMARD KEKRE offers best performance with FRR 30 % & FAR of 32%.
The performance offered by HADAMARD KEKRE HWT for HWT - 1 is better than HWT - 2. The performance
offered by HADAMARD combinations for HWT - 1 is better than HWT - 2. For HWT – 1, the performance offered by
all combinations of HADAMARD is better than Orthogonal HADAMARD transform. For HWT – 2, the performance
offered by all combinations of HADAMARD is better than Orthogonal HADAMARD transform

Best EER: EER in terms of training samples should be as low as possible. For HWT – 1, HADAMARD HAAR
transform offers best performance of 8 training samples compared to 9 training samples for orthogonal HADAMARD
wavelet transform. For HWT – 2, Orthogonal HADAMARD transform and HADAMARD DCT offer best performance
of 5 training samples compared to all combinations of HADAMARD HWT. The performance offered by HADAMARD
combinations for HWT - 2 is better than HWT - 1.

Best state wise FRR – FAR: FRR – FAR should be as low as possible for the given state from 2 to 5. For HWT - 1,
HADAMARD DHT offers best performance for 2 to 5 states. For HWT - 2, HADAMARD DHT offers best
performance for 2 and 4 states and HADAMARD KEKRE offers best performance for 3 and 5 states compared to
orthogonal HADAMARD transform. The performance offered by HADAMARD combinations for HWT - 1 is better
than HWT - 2.

Best Number of Symbol: It should be as low as possible. Testing was carried out for number of symbols from 200 to
750. It evident that the best performance in terms of FRR – FAR, AAR – ARR, EER is offered by 275 symbols for HWT
- 1 and 475-500 symbols for HWT - 2. The performance offered by HADAMARD combinations for HWT - 1 is better
than HWT - 2.

The comparison of HWT-1 and 2 for 1 – 16 bit for KEKRE combinations is shown in the Table V.Best FRR – FAR:
FAR should be as low as possible. For HWT - 1, KEKRE DCT, KEKRE HAAR and KEKRE128 offers best
performance with FRR & FAR of 0 %. For HWT - 2, KEKRE 128 offers best performance with FRR 5% & FAR of 2%.
The performance offered by KEKRE DCT, KEKRE HAAR and KEKRE128 HWT for HWT - 1 is better than HWT - 2.
The performance offered by HADAMARD combinations for HWT - 1 is better than HWT - 2. For HWT – 1, the
performance offered by KEKRE 128 is better than all combinations of KEKRE HWT. For HWT – 2, the performance
offered by KEKRE 128 is better than all combinations of KEKRE HWT.

Best EER: EER in terms of training samples should be as low as possible. For HWT – 1, KEKRE DHT offers best
performance of 11 training samples compared to 20 training samples for Orthogonal KEKRE transform. For HWT – 2,
KEKRE HADAMARD offers best performance of 6 training samples compared to 16 training samples for Orthogonal
KEKRE transform. The performance offered by DHT combinations for HWT - 2 is better than HWT - 1.

Best state wise FRR – FAR: FRR – FAR should be as low as possible for the given state from 2 to 5. For HWT - 1,
KEKRE 128 offers best performance for 2 TO 5 states compared to combinations of KEKRE HWT. For HWT - 2,
KEKRE 128 offers best performance for 2 TO 5 states compared to combinations of KEKRE HWT. The performance
offered by KEKRE combinations for HWT - 1 is better than HWT - 2.

Best Number of Symbol: It should be as low as possible. Testing was carried out for number of symbols from 200 to
750. It evident that the best performance in terms of FRR – FAR, AAR – ARR, EER is offered by 275 symbols for HWT
- 1 and 450 - 500 symbols for HWT - 2. The performance offered by HADAMARD combinations for HWT - 1 is better
than HWT - 2.

VOLUME 4, ISSUE 7, DEC/2017 150 http://iaetsdjaras.org/


IAETSD JOURNAL FOR ADVANCED RESEARCH IN APPLIED SCIENCES ISSN NO: 2394-8442

V. CONCLUSION
Comparing the various combinations of DCT, DHT, HAAR, HADAMARD and KEKRE for 1 – 16 samples of HWT
1 and 2 for pressure as feature vector we come to following conclusions:
1) FRR – FAR: For HWT - 1, DHT KEKRE, HAAR KEKRE, HADAMARD KEKRE, KEKRE HADAMARD
and KEKRE 128 best performance with FRR and FAR of 0 %. For HWT - 2 KEKRE 128 offers best performance with
FRR & FAR of 13 %. HWT - 1 offers better performance than HWT - 2.
2) EER: For HWT – 1, HADAMARD HAAR transform offers best performance of 8 training samples. For HWT –
2, Orthogonal DCT transform, DCT HADAMARD, DHT DCT and HAAR HADAMARD transform offers best
performance of 4 training samples. The performance offered by DCT combinations for HWT - 2 is better than HWT - 1.
3) State wise FRR – FAR: For HWT - 1, HAAR KEKRE, KEKRE HADAMARD and Orthogonal KEKRE
transform offers best performance for 2 to 5 states. For HWT - 2, KEKRE 128 offers best performance for 2 to 4 states
and DCT KEKRE 128 offers best performance for state 5. The performance offered by HWT - 1 is better than HWT - 2.
4) Number of Symbol: For HWT - 1 HAAR KEKRE, KEKRE HADAMARD and Orthogonal KEKRE offers best
performance at 300 symbols whereas for HWT - 2, best performance is at 500 symbols by KEKRE 128 and DCT
KEKRE.
5) HWT of DCT, HAAR, DHT, HADAMARD and KEKRE orthogonal transform offer better performance for
HWT - 1 than HWT - 2.
6) For HWT - 1 in terms of FRR-FAR, DCT KEKRE offers better performance than DCT orthogonal transform.
DHT DCT and DHT KEKRE offers better performance than DHT orthogonal transform. HAAR KEKRE offer better
performance than HAAR orthogonal transform. All combinations of HADAMARD HWT offers better performance than
HADAMARD orthogonal transform. KEKRE orthogonal transform offers better performance than all HWT of KEKRE
except KEKRE HADAMARD.
7) For HWT - 2 in terms of FRR-FAR, all combinations of DCT offer better performance than DCT orthogonal
transform. DHT KEKRE offers better performance than DHT orthogonal transform. HAAR DCT and HAAR KEKRE
offer better performance than HAAR orthogonal transform. All HWT of HADAMARD offer better performance than
HADAMARD orthogonal transform. KEKRE orthogonal transform offers better performance than all HWT of KEKRE.

REFERENCES
[1] A. K. Jain, A. Ross, S. Prabhakar, “An Introduction to Biometric Recognition”, IEEE Transactions on Circuits and Systems for
Video Technology, Vol. 14, No. 1, January 2004
[2] S. Nanavati, M. Thieme, and R. Nanavati, Biometrics: Identity Verification in a Networked World. New York: Wiley, 2002, pp.
123–131.
[3] T. Ohishi, Y. Komiya, H. Morita, and T. Matsumoto, “Pen-input online signature verification with position, pressure, inclination
trajectories,” in Proc. 15th Int. Parallel Distrib. Process. Symp. (IPDPS-15), San Francisco, CA, Apr. 2001, p. 170.
[4] [Online]. Available: www.cse.ust.hk/svc2004/download.html. [Accessed 1 January 2016].
[5] H B Kekre, T K Sarode, S D Thepade, “Inception of HWT using Two Orthogonal Transforms and It’s use for Image Compression”,
(IJCSIS) International Journal of Computer Science and Information Security, Vol. 9, No. 6, 2011
[6] Vinayak Ashok Bharadi, Vikas I. Singh and Bhushan Nemahe, “Hybrid Wavelets based Feature Vector Generation from
Multidimensional Data set for On-line Handwritten Signature Recognition” Proc.57th Int. Conf. Confluence The next Generation Information
Technology Sumit (Confluence) Noida, India, Nov. 2014.
[7] Dr. H.B.Kekre, Archana Athawale, Dipali Sadavarti, “Algorithm to generate Wavelet Transform from an orthogonal transform”,
International Journal of Image Processing (IJIP), vol. 4, no. 4, pp. 444–455, Oct. 2010
[8] L. Bovino, S. Impedovo, G. Pirlo, and L. Sarcinella, “Multi-expert verification of hand-written signatures,” in Proc. 7th Int. Conf. Doc.
Anal. Recognit. (ICDAR-7), IEEE Comput. Soc., Edinburgh, U.K., Aug. 2003, pp. 932–936.
[9] H. D. Chang, J. F. Wang, and H. M. Suen, “Dynamic handwritten Chinese signature verification,” in Proc. 2nd Int. Conf. Doc. Anal.
Recognit. (ICDAR-2), Tsukuba, Japan, Oct. 1993, pp. 258–261.
[10] Manoj Chavan, Ravish R Singh, Vinayak Bharadi, “Online Signature Verification using HWT with Hidden Markov Model” in Proc
4th International Conference on Computing, Communication, Control And Automation (ICCUBEA), Pune, India Aug 2017.

VOLUME 4, ISSUE 7, DEC/2017 151 http://iaetsdjaras.org/


IAETSD JOURNAL FOR ADVANCED RESEARCH IN APPLIED SCIENCES ISSN NO: 2394-8442

[11] Manoj Chavan, Ravish R Singh, Vinayak Bharadi, “Handwritten Signature Verification using Hidden Markov Model with HWT”
in Proc 4th International Conference on Computing, Communication, Control And Automation (ICCUBEA), Pune, India Aug 2017.
[12] E. J. R. Justino, F. Bortolozzi, and R. Sabourin, “A comparison of SVM and HMM classifiers in the offline signature verification,”
Pattern Recog- nit. Lett. vol. 26, pp. 1377–1385, 2005.
[13] A. P. Thad Starner, "Real-Time American Sign Language Visual Recognition From Video Using Hidden Markov Models," Master's
Thesis, MIT, Program in Media Art, Feb 1995.
[14] Donato Impedovo and Giuseppe Pirlo, "Automatic Signature Verification: The State of the Art," IEEE Transaction on Systems,
MAN and Cybernatics Part C: Application and Reviews, vol. Vol 28, no. No 5, September 2008.

VOLUME 4, ISSUE 7, DEC/2017 152 http://iaetsdjaras.org/