Writer verification based on a single handwriting word samples

Abstract

The writer recognition task has received a lot of interests during the last decade due to it wide range of applications. This task includes writer identification and/or writer verification. However, all the researches assumed that they dispose of a large amount of text to identify or authenticate the writer, which is never the case in real-life applications. In this paper, we present an original approach for the writer authentication task based on the analysis of a unique sample of a handwriting word. We used the Levenshtein edit distance based on Fisher-Wagner algorithm to estimate the cost of transforming one handwritten word into another. Such method has been successfully applied for signature authentication and voice recognition. In order to apply it to handwriting words, we developed a segmentation module to generate the graphemes; considered as elementary components for each word. We evaluated this approach on part of the IAM database (100 writers), where half of them provided three samples only of the same word. The obtained results are very promising since we succeed to accept correctly in 87 % of cases when we used the whole database (100 writers) and up to 92 % when we used 40 writers.

An integrated approach towards improvement of writer verification performance using page level, line level and word level data on Bangla handwritten document

“…They conducted an evaluation of their proposed method on three publicly available datasets, namely CVL, IAM, and Khatt, and achieved high performance on two of these datasets. The authors in [30] proposed the verification problem approach. The proposed approach is centered around analyzing a unique sample of a handwritten word and utilizes the Levenshtein edit distance, based on the Fisher-Wagner algorithm, to estimate the cost of transforming one handwritten word into another, specifically on the IAM database.…”

Attention based Writer Independent Handwriting Verification

“…However, the recently proposed deep learning models enabled automatic extraction of generic features. Ameur Bensefia [15] use Levenshtein edit distance based on Fisher-Wagner algorithm to estimate the cost of transforming one handwritten word into another, Shaikh et al [16] present a Hybrid Deep Learning architecture combining handcrafted features and Convolutional Neural Network (CNN) based features, Chu et al [17] propose an end-to-end deep learning method based on statistical features extracted on set-of-samples level.…”

Writer identification approach by holistic graphometric features using off-line handwritten words

“…This system reaches 95% for 50 users. In [17], it is showed a Levenshtein edit distance based on Fisher-Wagner algorithm to estimate the cost of transforming one handwritten word applied to two datasets of 100 and 40 users and reaching 87 and 40% respectively.…”