Off-line writer verification based on simple graphemes

Aubin, Verónica I.; Mora, Marco; Santos-Peñas, Matilde

doi:10.1016/j.patcog.2018.02.024

Cited by 29 publications

(17 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Adak and Chaudhuri [29] study the writer identification based on the isolated characters and numerals. Aubin et al [30] propose a writer identification method based on the simple graphemes or single strokes. These methods extract several handcrafted descriptors on characters or strokes and SVM is used for recognizing the writer identity.…”

Section: Related Workmentioning

confidence: 99%

FragNet: Writer Identification Using Deep Fragment Networks

Schomaker

2020

IEEE Trans.Inform.Forensic Secur.

View full text Add to dashboard Cite

Writer identification based on a small amount of text is a challenging problem. In this paper, we propose a new benchmark study for writer identification based on word or text block images which approximately contain one word. In order to extract powerful features on these word images, a deep neural network, named FragNet, is proposed. The FragNet has two pathways: feature pyramid which is used to extract feature maps and fragment pathway which is trained to predict the writer identity based on fragments extracted from the input image and the feature maps on the feature pyramid. We conduct experiments on four benchmark datasets, which show that our proposed method can generate efficient and robust deep representations for writer identification based on both word and page images.

show abstract

Section: Related Workmentioning

confidence: 99%

FragNet: Writer Identification Using Deep Fragment Networks

Schomaker

2020

IEEE Trans.Inform.Forensic Secur.

View full text Add to dashboard Cite

show abstract

“…With MSHD datasets, they reported a classification accuracy of 79.9% and 79% with SVM and NN, respectively. Aubin et al [20] proposed a novel method for the verification of personal identity based on handwritten strokes. They performed the task on the offline data and proposed a new descriptor to measure the relative position of the darkest points by processing the single and simple graphemes.…”

Section: Related Workmentioning

confidence: 99%

Hybrid Features for Gender Classification System based on Pre-segmented Handwritten Gurumukhi Characters Using Machine Learning Algorithms

SINGLA

Maini

Kumar

2023

Preprint

View full text Add to dashboard Cite

Identification of handwriting has been an evolving task for mitigating specific issues in the fields of machine learning and pattern recognition. In the fields of artificial intelligence and machine learning, a gender classification method based on one or more features has emerged as a promising idea for addressing issues such as criminal, forensic, and suspected examinations. Predicting an individual's age, gender, and handedness based on their handwriting is one of the more challenging offline handwriting applications. The authors have presented a novel approach to classifying gender as male or female based on pre-segmented Gurumukhi (Punjabi) characters using feature extraction methods and classification algorithms such as K-NN, random forest, SVM, and MLPs in this proposed work. On a dataset of about 72,000 Gurumukhi characters, we extracted diagonal, transition, zoning, and peak extent based features (which consists of 280 writers with 150 males and 130 females). Our results show that by using a hybridization of multiple feature extraction techniques, the random forest classifier achieves higher accuracy than other classifiers.

show abstract

“…Previous studies [37][38][39][40] have focused on time or stroke features of handwriting. A writer recognition system for touch-screen mobile devices was proposed in Reference [37] for non-Latin languages with a large set of characters. Therefore, the authors avoid complex time-intensive algorithms like Multilayer Perceptron, Support Vector Machine or Hidden Markov Model.…”

Section: Of 25mentioning

confidence: 99%

Writer Identification Using Handwritten Cursive Texts and Single Character Words

et al. 2019

View full text Add to dashboard Cite

One of the biometric methods in authentication systems is the writer verification/identification using password handwriting. The main objective of this paper is to present a robust writer verification system by using cursive texts as well as block letter words. To evaluate the system, two datasets have been used. One of them is called Secure Password DB 150, which is composed of 150 users with 18 samples of single character words per user. Another dataset is public and called IAM online handwriting database, and it is composed of 220 users of cursive text samples. Each sample has been defined by a set of features, composed of 67 geometrical, statistical, and temporal features. In order to get more discriminative information, two feature reduction methods have been applied, Fisher Score and Info Gain Attribute Evaluation. Finally, the classification system has been implemented by hold-out cross validation and k-folds cross validation strategies for three different classifiers, K-NN, Naïve Bayes and Bayes Net classifiers. Besides, it has been applied for verification and identification approaches. The best results of 95.38% correct classification are achieved by using the k-nearest neighbor classifier for single character DB. A feature reduction by Info Gain Attribute Evaluation improves the results for Naïve Bayes Classifier to 98.34% for IAM online handwriting DB. It is concluded that the set of features and its reduction are a strong selection for the based-password handwritten writer identification in comparison with the state-of-the-art.

show abstract

Off-line writer verification based on simple graphemes

Cited by 29 publications

References 33 publications

FragNet: Writer Identification Using Deep Fragment Networks

FragNet: Writer Identification Using Deep Fragment Networks

Hybrid Features for Gender Classification System based on Pre-segmented Handwritten Gurumukhi Characters Using Machine Learning Algorithms

Writer Identification Using Handwritten Cursive Texts and Single Character Words

Contact Info

Product

Resources

About