Writer Identification Using Siamese Networks and Character-Level Analysis

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26220%2F26%3A0199901" target="_blank" >RIV/00216305:26220/26:0199901 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/00007064:K01__/25:N0000038

Výsledek na webu

<a href="http://dx.doi.org/10.1109/ICUMT67815.2025.11268620" target="_blank" >http://dx.doi.org/10.1109/ICUMT67815.2025.11268620</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICUMT67815.2025.11268620" target="_blank" >10.1109/ICUMT67815.2025.11268620</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Writer Identification Using Siamese Networks and Character-Level Analysis

Popis výsledku v původním jazyce

Writer identification of handwritten text is a task in forensic document analysis, traditionally relying on visual comparison by experts. However, this process is time-consuming and subjective. Although the amount of crime involving handwriting has remained constant, the overall volume of handwritten material has decreased. This paper presents an approach based on a Siamese Neural Network (SNN) to writer identification by analyzing a limited information source - just a single character – A – from samples of Czech handwriting. The main contributions are: (i) the design of an SNN with a five-block convolutional branch combined with voting strategies incorporating an uncertainty zone; and (ii) a detailed experimental comparison of over 400 architecture and hyperparameter configurations in terms of accuracy, F1-score, and decision efficiency. The best model achieved relatively high accuracy – 96.1 % accuracy and a F1-score of 0.932 while abstaining from classification in approximately 57% of ambiguous cases. The trade-off between classification confidence and coverage, the limitations of single-character analysis, and the potential for generalization to open-set scenarios and multimodal inputs are discussed. The proposed approach offers an objective and reproducible method suitable for forensic handwriting analysis.

Název v anglickém jazyce

Writer Identification Using Siamese Networks and Character-Level Analysis

Popis výsledku anglicky

Writer identification of handwritten text is a task in forensic document analysis, traditionally relying on visual comparison by experts. However, this process is time-consuming and subjective. Although the amount of crime involving handwriting has remained constant, the overall volume of handwritten material has decreased. This paper presents an approach based on a Siamese Neural Network (SNN) to writer identification by analyzing a limited information source - just a single character – A – from samples of Czech handwriting. The main contributions are: (i) the design of an SNN with a five-block convolutional branch combined with voting strategies incorporating an uncertainty zone; and (ii) a detailed experimental comparison of over 400 architecture and hyperparameter configurations in terms of accuracy, F1-score, and decision efficiency. The best model achieved relatively high accuracy – 96.1 % accuracy and a F1-score of 0.932 while abstaining from classification in approximately 57% of ambiguous cases. The trade-off between classification confidence and coverage, the limitations of single-character analysis, and the potential for generalization to open-set scenarios and multimodal inputs are discussed. The proposed approach offers an objective and reproducible method suitable for forensic handwriting analysis.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20203 - Telecommunications

Projekt

<a href="/cs/project/VJ02010019" target="_blank" >VJ02010019: Nástroje forenzní expertizy ručně psaného písma</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

2025 17th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT)

ISBN

979-8-3315-7675-2

ISSN

—

e-ISSN

—

Počet stran výsledku

5

Strana od-do

182-186

Název nakladatele

IEEE

Místo vydání

Italy

Místo konání akce

Florence, Italy

Datum konání akce

3. 11. 2025

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—