Katrin Franke

A computer-based system to support forensic studies on handwritten documents

Abstract. Computer-based forensic handwriting analysis requires sophisticated methods for the pre-processing of digitized paper documents, in order to provide high-quality digitized handwriting, which represents the original handwritten product as accurately as possible. Due to the requirement of processing a huge amount of different document types, neither a standardized queue of processing stages, fixed parameter sets nor fixed image operations are qualified for such pre-processing methods. Thus, we present an open layered framework that covers adaptation abilities at the parameter, operator, and algorithm levels. Moreover, an embedded module, which uses genetic programming, might generate specific filters for background removal on-the-fly. The framework is understood as an assistance system for forensic handwriting experts and has been in use by the Bundeskriminalamt, the federal police bureau in Germany, for two years. In the following, the layered framework will be presented, fundamental document-independent filters for textured, homogeneous background removal and for foreground removal will be described, as well as aspects of the implementation. Results of the framework-application will also be given.

Automatic writer identification using fragmented connected-component contours

In this paper, a method for off-line writer identification is presented, using the contours of fragmented connected components in mixed-style handwritten samples of limited size. The writer is considered to characterized by a stochastic pattern generator, producing a family of character fragments (fraglets). Using a codebook of such fraglets from an independent training set, the probability distribution of fraglet contours was computed for an independent test set. Results revealed a high sensitivity of the fraglet histogram in identifying individual writers on the basis of a paragraph of text. Large-scale experiments on the optimal size of Kohonen maps of fraglet contours were performed, showing usable classification rates within a non-critical range of Kohonen map dimensions. Further validation experiments on variable-sized random subsets from an independent set of 215 writers gives additional support for the proposed method. The proposed automatic approach bridges the gap between image statistics approaches and manual character-based methods.

Ink texture analysis for writer identification

This paper presents an approach for ink type recognition. Ink type classes will be derived from the physical properties of ink. Ink specific trace morphologies are considered as textures. From these discriminant texture features of the co-occurrence matrix will be derived. The proposed method for automated ink type recognition was tested using 62 different kinds of pens and refills. The achieved recognition result of 99.7% for 600 dpi and 98.4% for 300 dpi handwritings further promotes the study of trace morphologies in particular for application in forensic writer identification.

Ink-deposition model: the relation of writing and ink deposition processes

The paper describes our studies on the influence of physical and biomechanical processes on the ink trace and aims at providing a solid foundation for enhanced signature analysis procedures. By means of a writing robot, simulated human handwriting movements are considered to study the relation between writing process characteristics and ink deposit on paper. Since the robot is able to take up different writing instruments like pencil, ballpoint or fine line pen, the type of inking pen was also varied in the experiments. The results of analyzing these artificial ink traces contribute to a better understanding of the underlying interaction processes and allow for the formulation of a so-called ink-deposition model (IDM). Particularly, we present IDMs that analytically describe the relation of applied pen tip force and relative ink intensity distribution for solid, viscous and fluid ink types. These IDMs might be employed in computer-based analysis of ink trace line quality to recognize skilled forgeries.

Tiny GAs for image processing applications

The expedience of todays image-processing applications is no longer based on the performance of a single algorithm alone. These systems appear to be complex frameworks with a lot of sub-tasks that are solved by specific algorithms, adaptation procedures, data handling, scheduling, and parameter choices. The venture of using computational intelligence (CI) in such a context, thus, is not a matter of a single approach. Among the great choice of techniques to inject CI in an image-processing framework, the primary focus of this presentation will be on the usage of so-called tiny-GAs. This stands for an evolutionary procedure with low efforts, i.e. small population size (like 10 individuals), little number of generations, and a simple fitness. Obviously, this is not suitable for solving highly complex optimization tasks, but the primary interest here is not the best individuals fitness, but the fortune of the algorithm and its population, which has just escaped the Monte-Carlo domain after random initialization. That this approach can work in practice will be demonstrated by means of selected image-processing applications, especially in the context of linear regression and line fitting; evolutionary post processing of various clustering results, in order to select a most suitable one by similarity; and classification by the fitness values obtained after a few generations

Fuzzy image processing by using Dubois and Prade fuzzy norms

This paper presents new image processing operations based on the Dubois and Prade (1980) proposal of a fuzzy triangular norm. This definition is recalled, and a computational efficient algorithm is derived for its fast computation. This procedure also gives a comprehensive model for reasoning about the qualitative effects of the Dubois and Prade fuzzy norm on data. The presented image processing operations can be considered as fuzzy morphology operations. Due to this fact the application modes for those operations can be judged. Using the Dubois and Prade fuzzy morphology for background removal on bank cheque images is demonstrated as an application.

Biometric User Authentication on Smart Cards by Means of Handwritten Signatures

This paper describes a biometric method for user authentication on smart cards. Smart cards are chip cards with the ability for data processing directly on the card. They are not only usable for storing biometric reference data, but biometric user authentication methods can also be performed on card in order to protect security-relevant functions or data on the cards. The biometric data under consideration are handwritten signatures captured by means of a graphic tablet and a special pen. The feature-matching algorithm is a variant of dynamic time warping, taking the limited resources of smart cards into account. It is implemented as an operating prototype on two types of smart cards.

Verification of video source camera competition (CAMCOM 2010)

Digital cameras are being integrated in a large number of mobile devices. These devices may be used to record illegal activities, or the recordings themselves may be illegal. Due to the tight integration of these mobile devices with the internet, these recordings may quickly find their way to internet video-sharing sites such as YouTube. In criminal casework it is advantageous to reliably establish the source of the video. Although this was shown to be doable for relatively high quality video, it is unknown how these systems perform for low quality transcoded videos. The CAMCOM2010 contest is organized to create a benchmark for source video identification, where the videos originate from YouTube. Despite the number of participants was satisfactory initially, only two participants submitted results, mostly due to a lack of time. Judging by the performance of the contestants, this is certainly not a trivial problem.

Pen force emulating robotic writing device and its application

The paper describes our studies on the influence of physical and biomechanical processes on the ink trace and aims at providing a solid foundation for enhanced signature analysis procedures. By means of a writing robot, simulated human handwriting movements are considered to study the relation between writing process characteristics and ink deposit on paper. Since the robot is able to take up different writing instruments like pencil, ballpoint or fine line pen, the type of inking pen was also varied in the experiments. The results of analyzing these artificial ink traces contribute to a better understanding of the underlying interaction processes and find its applications in the teaching, training, and forensic investigation. It comes out that position, velocity and pen force suffice to produce high quality ink traces, hardly distinguishable from original probes.

The WANDAML markup language for digital document annotation

WANDAML is an XML-based markup language for the annotation and filter journaling of digital documents. It addresses in particular the needs of forensic handwriting data examination, by allowing experts to enter information about writer, material (pen, paper), script and content, and to record chains of image filtering and feature extraction operations applied to the data. Annotations may be organized in a structure that reflects the document layout via a hierarchy of document regions. WANDAML lends itself to a variety of applications, including the annotation all kinds of handwriting documents (on-line or off-line), images of printed text, medical images, and satellite images.