Handwritten signature verification is the process of confirming
the identity of a user based on his or her handwritten signature.
Automatic handwritten signature verification is not a new problem.
Many early research attempts were reviewed in the survey papers,
e.g., [Plamondon and Lorette 1989; Leclerc and Plamondon 1994].
The primary advantage that signature verification has over other
types of biometric technologies is that signature is already the
most widely accepted biometric for identity verification. The long
history of trust over signature verification means that people are
very willing to accept a signature-based biometric authentication
However, there has not been any major international effort that
aims at comparing different signature verification methods
systematically. As common benchmark databases and benchmarking
rules are often used by researchers in such areas as information
retrieval and natural language processing, researchers in
biometrics increasingly see the need for such common benchmarks
for comparative studies. For example, fingerprint verification
competitions were organized twice (FVC2000 and FVC2002) to attract
participants from both academia and industry to compare their
algorithms objectively. As inspired by these efforts, we are
organizing the first international competition on handwritten
signature verification. We intend to make this an important event
for both academics and industrialists working in this challenging
[Leclerc and Plamondon 1994] F. Leclerc and R. Plamondon.
Automatic signature verification: the state of the art
1989-1993. International Journal of Pattern Recognition and
Artificial Intelligence, 8(3):643-660, 1994.
[Plamondon and Lorette 1989] R. Plamondon and G. Lorette.
Automatic signature verification and writer identification the
state of the art. Pattern Recognition, 22(2):107-131, 1989.