Institute, Warsaw, Poland This paper describes the results of the IEEE BigData 2023 Keystroke Verification Challenge1(KVC), that considers the biometric verification performance of Keystroke Dynamics (KD), captured as tweet-long sequences of variable transcript text from over 185,000 subjects. The data are obtained from two of the largest public databases of KD up to date, the Aalto Desktop and Mobile Keystroke Databases, guaranteeing a minimum amount of data per subject, age and gender annotations, absence of corrupted data, and avoiding excessively unbalanced subject distributions with respect to the considered demographic attributes. Several neural architectures were proposed by the participants, leading to global Equal Error Rates (EERs) as low as 3.33% and 3.61% achieved by the best team respectively in the desktop and mobile scenario, outperforming the current state of the art biometric verification performance for KD. Hosted on CodaLab2, the KVC will be made ongoing to represent a useful tool for the research community to compare different approaches under the same experimental conditions and to deepen the knowledge of the field.

Data have become one of the most valuable things in this new era where deep learning technology seems to overcome traditional approaches. However, in some tasks, such as the verification of handwritten signatures, the amount of publicly available data is scarce, what makes difficult to test the real limits of deep learning. In addition to the lack of public data, it is not easy to evaluate the improvements of novel approaches compared with the state of the art as different experimental protocols and conditions are usually considered for different signature databases. To tackle all these mentioned problems, the main contribution of this study is twofold: i) we present and describe the new DeepSignDB on-line handwritten signature biometric public database, and ii) we propose a standard experimental protocol and benchmark to be used for the research community in order to perform a fair comparison of novel approaches with the state of the art. The DeepSignDB database is obtained through the combination of some of the most popular on-line signature databases, and a novel dataset not presented yet. It comprises more than 70K signatures acquired using both stylus and finger inputs from a total of 1526 users. Two acquisition scenarios are considered, office and mobile, with a total of 8 different devices. Additionally, different types of impostors and number of acquisition sessions are considered along the database. The DeepSignDB and benchmark results are available in GitHub.

Script identification is an important step in multi-script document analysis. As different textures present in text portion of a script are the main distinct features of the script, in this paper, we proposed a new algorithm for printed script identification based on texture analysis. Since local patterns is a unifying concept for traditional statistical and structural approaches of texture analysis, here the basic idea is to use the histogram of the local patterns as description of the script stroke directions distribution which is the characteristic of every script. As local pattern, the basic version of the Local Binary Patterns (LBP) and a modified version of the Orientation of the Local Binary Patterns (OLBP) are proposed. A Least Square Support Vector Machine (LS-SVM) is used as identifier. The scheme has been verified on two databases. The first or training database is a database with 200 sheets of 10 different scripts. The scripts font is provided by the Google translator. The second or test database has been obtained by scanning different newspapers and books. It contains 5 common scripts among 10 different scripts of the first database. From the experiment we obtained encouraging results.

The automatic handwritten signature verification is an open problem for the scientific community. The most of the published studies examine a generic document trying to locate where the signature has been written, to segment the signature removing complex backgrounds containing lines and letter and to determining whether the signature was made by the owner. However, there are no studies to determine automatically the author of a fake. This paper presents a first approach to the identification of a static signature forger. The underlying hypothesis is the fact that a forger finds difficult to fight against their own free natural way of writing, leading to the second hypothesis that under several conditions it is possible to isolate these features to determine a fake within a population of known forgers. The experiments shown that gray level based features are a good start point to detect who has written the signatures.