Investigation of adaptive local threshold segmentation in context of 3D-handwriting forensics

Kalbitz, Michael; Scheidat, Tobias; Vielhauer, Claus

doi:10.1109/ipta.2016.7821000

Cited by 1 publication

(8 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As related to the previous works of authors [3–5], this article combines and extends the state of the art in the following ways: application of the sensing methodology and the global threshold segmentation approach suggested in [3], optimisation of process parameter combinations , determined by the benchmark procedure introduced in [5] and subsequent biometric and forensic evaluation , using data obtained by biometric as well as forensic sensors as proposed in [4]. Further, the databases used within the three publications as well as the two biometric feature sets introduced in [4] are extended within this article to provide more significant results: iv.…”

Section: Related Workmentioning

confidence: 62%

“…As related to the previous works of authors [3][4][5], this article combines and extends the state of the art in the following ways:…”

Section: Related Workmentioning

confidence: 87%

“…There are two main goals focused in the work described in this paper. Firstly, expanding the experimental studies from [3][4][5] by significantly extended experiments, comparing the biometric authentication performance based on forensic handwriting data to those sampled by a special biometric device developed for handwriting modality. The second aim is to study principals and effects of local parameter optimisation for the pre-processing steps of the data acquired by the CWL sensor.…”

Section: Methodsmentioning

confidence: 99%

“…application of the sensing methodology and the global threshold segmentation approach suggested in [3], ii. optimisation of process parameter combinations, determined by the benchmark procedure introduced in [5] and iii. subsequent biometric and forensic evaluation, using data obtained by biometric as well as forensic sensors as proposed in [4].…”

Section: Related Workmentioning

confidence: 99%

“…In this article, authors will extend their initial works [3–5] in these fields by presenting an adoption of features from the concept of biometric hashing of online signatures [2] towards forensic handwriting traces, as recently proposed in [4]. Following the characteristics of data provided by the 2D/3D forensic sensor, adopted biometric features have to be limited to time independent features based on pressure and/or spatial information.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Biometric authentication based on 2D/3D sensing of forensic handwriting traces

2017

Self Cite

View full text Add to dashboard Cite

Handwriting represents an important modality in both biometric and forensic domains. while the first field appears to be a well-studied area with many approaches for acquisition, feature extraction and classification, the latter is rather novel with respect to digitised, automated methods. In prior works, authors of this article have shown that forensic handwriting traces can be processed by means of high-resolution 2D/3D surficial scanners. These devices allow the acquisition at a vertical resolution down to a few nanometres. Pre-processing methods have been identified, which allow for spatial segmentation of writing traces and for de-noising of 2D and 3D data, leading to a clear visual enhancement of the writing traces based on topography information. Further, authors have suggested a novel benchmarking method for forensic trace analysis based on feature sets originally suggested for biometric handwriting and comparing the forensic recognition performance by means of equal error rates, achieved from biometric sensors and forensic 2D/3D sensors in parallel. This article summarises and extents these works in two main aspects: on one side, it presents significantly extended experiments with respect to test set size and feature sets utilised for classification. On the other side, authors suggest new optimisation approaches to the segmentation algorithm.

show abstract