Éditeur(s) : HAL CCSD
Résumé : International audience
This paper presents the early work, done in the context of the IntuiScript project, on handwriting quality analysis. This IntuiScript project aims at developing a digital workbook to help with teaching children how to handwrite. To do so, we must be able to analyse their handwriting, to evaluate if the letters are correctly written, and to detail what aspects of the child symbols – letters, numbers, and geometric forms-do not correspond to the teacher models. We use an online fuzzy model to easily build target models, and to automatically evaluate the adequacy of children letters to these reference models, with respect to different aspects: symbol shape, drawing direction and stroke order for example.
17th Biennial Conference of the International Graphonomics Society
Pointe-à-Pitre, Guadeloupe

Droits : info:eu-repo/semantics/OpenAccess
hal-01165765
https://hal.univ-antilles.fr/hal-01165765
https://hal.univ-antilles.fr/hal-01165765/document
https://hal.univ-antilles.fr/hal-01165765/file/IGS_2015_submission_4.pdf

Éditeur(s) : HAL CCSD
Résumé : International audience
This paper presents an experimental investigation on stability and complexity of dynamic signatures. A technique based on multiple matching strategies using Dynamic Time Warping is considered to derive both stability and complexity information from dynamic signatures. The experimental results, carried out on signatures of the SUSIG database, highlight some interesting characteristics on handwritten signatures.
17th Biennial Conference of the International Graphonomics Society
Pointe-à-Pitre, Guadeloupe

hal-01165912
https://hal.univ-antilles.fr/hal-01165912
https://hal.univ-antilles.fr/hal-01165912/document
https://hal.univ-antilles.fr/hal-01165912/file/IGS_2015_submission_29.pdf

Éditeur(s) : HAL CCSD
Résumé : International audience
We propose in this paper a new online Multi-UserMulti-Touch handwritten diagram DataBase (MUMTDB) forevaluating recognition systems under the multi-user situation.The data is collected according to two predefined mind mapscenarios which contains 9 classes of graphical symbols. Eachscenario is completed by involving two users at the same time.Since the users are given freedom to draw the symbols asthey want, the dataset contains a diversity of multi-stroke andeven multi-touch symbols. It allows addressing new challengingproblems regarding the recognition of simultaneous composition of structured documents. The dataset is freely availableon-line.
International Conference on Frontiers in Handwriting Recognition (ICFHR)
Shenzhen, China

hal-01374376
https://hal.univ-antilles.fr/hal-01374376

Éditeur(s) : HAL CCSD
Résumé : International audience
This paper deals with the study of the kinematic dimension of scribbling activities executed by kindergarten children aged from 3 to 6 years old from three grades. For this purpose, three sigma-lognormal features, six classical ones and one hybrid feature related to visuo-motor skills are extracted from scribbles realized using five different Type Grib. The statistical analysis of these data illustrates that sigma-lognormal modeling can satisfactorily reconstruct kindergarten children’s scribbles. Moreover, this preliminary study confirms that there are significant differences between grades with respect to six of the features we studied, regardless of the nature of the scribbling movement made by children. These features are related to rapidity, fluidity and precision of linear and curvilinear movements used for scribbling tasks.
17th Biennial Conference of the International Graphonomics Society
Pointe-à-Pitre, Guadeloupe

hal-01165910
https://hal.univ-antilles.fr/hal-01165910
https://hal.univ-antilles.fr/hal-01165910/document
https://hal.univ-antilles.fr/hal-01165910/file/IGS_2015_submission_28.pdf

Éditeur(s) : HAL CCSD
Résumé : International audience
Pen-based interfaces allow users to interact with the help of a stylus and/or fingers. Thanks to a recognition system, users can execute commands by drawing gestures. Because of the complexity of the software, the set of gesture commands can be very large. Consequently, it becomes difficult for the users to remember all the commands. In this paper we introduce "Semicustomizable gestural commands". The idea is to take into account the commands usage frequency: to facilitate the memorization of the most used commands we leave users the freedom/liberty to define their associated gestures (by) themselves. The remaining gesture commands will be automatically generated on the base of the defined gestures according to their hierarchical categorization. Several comparative tests demonstrate that this new approach improved the progressive memorization of the gestural commands.
ICFHR 2012 - International Conference on Frontiers in Handwriting Recognition
Bari, Italy

hal-00708750
https://hal.inria.fr/hal-00708750
https://hal.inria.fr/hal-00708750/document
https://hal.inria.fr/hal-00708750/file/ICFHR_LI_IEEE.pdf

Éditeur(s) : HAL CCSD
Résumé : International audience
This paper examines the historical signatures of 18th century composer, J. S. Bach, to evaluate the effects of vision impairment on handwritten signatures. It is questioned whether Bach penned certain signatures as it is historically documented that he was virtually blind in the years just prior to his death in 1750. Applying information collected from published forensic studies about the effects of vision impairment on handwriting, handwriting indices of vision impairment are compared to Bach's signatures in the late 1740s.
17th Biennial Conference of the International Graphonomics Society
Pointe-à-Pitre, Guadeloupe

hal-01165902
https://hal.univ-antilles.fr/hal-01165902
https://hal.univ-antilles.fr/hal-01165902/document
https://hal.univ-antilles.fr/hal-01165902/file/IGS_2015_submission_25.pdf

Éditeur(s) : HAL CCSD
Résumé : International audience
Handwriting difficulties represent a common cause of underachievement in children education and low self-esteem in daily life. The analysis of handwriting could be an important tool for the evaluation of a teaching method in order to assess its efficacy in preventing dysgraphia. We performed a comparative analysis of the traditional handwriting method and the alternative Terzi's approach in pupils at the end of primary school, when cursive skills should have been achieved.Qualitative and kinematic parameters were considered: the first ones were calculated as a visual analysis of written texts (by using check-lists and scales regarding qualitative, postural and pen grasp aspects), while the latter ones were automatically extracted through digitizing tablet acquisitions. Results showed significant differences concerning handwriting quality and dynamic movement in pupils handwriting depending on the teaching method applied.
17th Biennial Conference of the International Graphonomics Society
Pointe-à-Pitre, Guadeloupe

hal-01165776
https://hal.univ-antilles.fr/hal-01165776
https://hal.univ-antilles.fr/hal-01165776/document
https://hal.univ-antilles.fr/hal-01165776/file/IGS_2015_submission_10.pdf

Éditeur(s) : HAL CCSD
Résumé : International audience
Extract the features for a multi-touch gesture is difficult due to the complex temporal and motion relations between multiple trajectories. In this paper we present a new generic graph model to quantify the shape, temporal and motion information from multi-touch gesture. To make a comparison between graph, we also propose a specific graph matching method based on graph edit distance. Results prove that our graph model can be fruitfully used for multi-touch gesture pattern recognition purpose with the classifier of graph embedding and SVM.
17th Biennial Conference of the International Graphonomics Society
Pointe-à-Pitre, Guadeloupe

hal-01165768
https://hal.univ-antilles.fr/hal-01165768
https://hal.univ-antilles.fr/hal-01165768/document
https://hal.univ-antilles.fr/hal-01165768/file/IGS_2015_submission_6.pdf

Éditeur(s) : HAL CCSD
Résumé : International audience
Some research on written production has focused on the role of the syllable as a processing unit. However, the precise nature of this syllable unit has yet to be elucidated. The present study examined whether the nature of this processing unit is orthographic (i.e., the ortho-syllable) or phonological. Thirty-two native French speakers were asked to copy adjectives on a digitizer, successively adding a plural and a feminine one-letter morpheme to the same adjective. The adjective agreement could modify the structure of both phonological and orthographic syllables, only ortho-syllabic structure, or leave both unchanged. When the change modified only the orthographic syllable structure, there was an increase in duration at the letter before the syllable boundary. By contrast, when adding a letter changed both orthographic and phonological structures, an increase in the duration of the inter-letter interval was observed. Importantly, the increase in duration cannot be explained exclusively by the addition of a letter because the addition of a plural inflection did not significantly influence the dynamics of handwritten production. These results are consistent with the idea that ortho-syllables serve as a processing unit during handwriting, and that this type of syllable is specific to the written code.
17th Biennial Conference of the International Graphonomics Society
Pointe-à-Pitre, Guadeloupe

hal-01165879
https://hal.univ-antilles.fr/hal-01165879
https://hal.univ-antilles.fr/hal-01165879/document
https://hal.univ-antilles.fr/hal-01165879/file/IGS_2015_submission_14.pdf

Éditeur(s) : HAL CCSD
Résumé : International audience
In this paper, we present a novel method for recognition of handwritten sketches. Unlike previous approaches, we focus on online retrieval and ability to build our model incrementally, thus we do not need to know all the data in advance and we can achieve very good recognition results after as few as 15 samples. The method is composed of two main parts: feature representation and learning and recognition. In feature representation part, we utilize SIFT-like feature descriptors in combination with soft response Bag-of-Words techniques. Descriptors are extracted locally using our novel sketch-specific sampling strategy and for support regions we follow patch-based approach. For learning and recognition, we use a novel technique based on fuzzy-neural networks, which has shown good performance in incremental learning. The experiments on state-of-the-art benchmarks have shown promising results.
17th Biennial Conference of the International Graphonomics Society
Pointe-à-Pitre, Guadeloupe

hal-01166497
https://hal.univ-antilles.fr/hal-01166497
https://hal.univ-antilles.fr/hal-01166497/document
https://hal.univ-antilles.fr/hal-01166497/file/IGS_2015_submission_37.pdf

Éditeur(s) : HAL CCSD
Résumé : International audience
The Sigma-Lognormal model of the Kinematic Theory of rapid human movements allows us to represent on-line signatures with an analytical neuromuscular model. It has been successfully used in the past to generate synthetic signatures in order to improve the performance of an automatic verification system. In this paper, we attempt for the first time to build a verification system based on the model parameters themselves. For describing individual lognormal strokes, we propose eighteen features which capture cognitive psychomotor characteristics of the signer. They are matched by means of dynamic time warping to derive a dissimilarity measure for signature verification. Promising initial results are reported for an experimental evaluation on the SUSIG visual sub-corpus, which contains some of the most skilled forgeries currently available for research.
17th Biennial Conference of the International Graphonomics Society
Pointe-à-Pitre, Guadeloupe

hal-01165871
https://hal.univ-antilles.fr/hal-01165871
https://hal.univ-antilles.fr/hal-01165871/document
https://hal.univ-antilles.fr/hal-01165871/file/IGS_2015_submission_11.pdf

Éditeur(s) : HAL CCSD
Résumé : International audience
Advances in technology and scientific development in forensic handwriting examination (FHE) require a review in response to the challenges published in the NAS Report. This survey summarizes the advances made in theoretical and methodological approaches to handwriting examination including a review of research on the proficiency of FHEs. Technology has impacted FHE including analysis of e-signatures and use of technology for signature and handwriting authentication. A review of legal cases in the U.S. confirms how research and technological advances have met legal challenges and impacted decisions in the courtroom.
17th Biennial Conference of the International Graphonomics Society
Pointe-à-Pitre, Guadeloupe

hal-01165905
https://hal.univ-antilles.fr/hal-01165905
https://hal.univ-antilles.fr/hal-01165905/document
https://hal.univ-antilles.fr/hal-01165905/file/IGS_2015_submission_26.pdf

Éditeur(s) : HAL CCSD
Résumé : International audience
An investigation of the eye and hand movement during the task of signature simulation was conducted. Three subjects' eye movements and hand movements were recorded using an eye-tracker and a digitizing tablet while they simulated signatures. The study revealed that eye gaze most frequently shifted within less than 17 msec of a pen velocity minimum. It is thought that the cognitive processes overseeing this movement control and the limitations of the visuomotor buffer could play an important role in the behaviour of simulating signatures and signature simulation quality.
17th Biennial Conference of the International Graphonomics Society
Pointe-à-Pitre, Guadeloupe

hal-01166493
https://hal.univ-antilles.fr/hal-01166493
https://hal.univ-antilles.fr/hal-01166493/document
https://hal.univ-antilles.fr/hal-01166493/file/IGS_2015_submission_35.pdf

Éditeur(s) : HAL CCSD
Résumé : International audience
Signatures are one of the most accessible and prevailed ways of authenticating documents.Over the last many years, a large number of signature verication systems have been reported. Acommon assumption in nearly all of these system is that the signatures are available readily extractedfrom documents. In this paper we provide a detailed literature survey on the subject and arguethat pre-extracted signatures are not always available especially in forensic cases. Furthermore, wepresent a novel system of automatically extracting signatures from documents with the help ofhyper-spectral imaging. Initial experiments reveal that the proposed idea possess great potential toform a baseline signature extraction system above whom any signature verication system can beadjuncted for signature verication.
17th Biennial Conference of the International Graphonomics Society
Pointe-à-Pitre, Guadeloupe

hal-01165888
https://hal.univ-antilles.fr/hal-01165888
https://hal.univ-antilles.fr/hal-01165888/document
https://hal.univ-antilles.fr/hal-01165888/file/IGS_2015_submission_18.pdf

Éditeur(s) : HAL CCSD
Résumé : International audience
The development of predictive tools has been commonly utilized as the most effective manner to prevent illnesses thatstrike suddenly. Within this context, investigations linking fine human motor control with brain stroke risk factors areconsidered to have a high potential but they are still in an early stage of research. The present paper analysesneuromuscular features of oscillatory movements based on the Omega-Lognormal model of the Kinematic Theory. On adatabase of oscillatory movements from 120 subjects, we demonstrate that the proposed features differ significantlybetween subjects with and without brain stroke risk factors. This promising result motivates the development ofpredictive tools based on the Omega-Lognormal model.
17th Biennial Conference of the International Graphonomics Society
Pointe-à-Pitre, Guadeloupe

hal-01165773
https://hal.univ-antilles.fr/hal-01165773
https://hal.univ-antilles.fr/hal-01165773/document
https://hal.univ-antilles.fr/hal-01165773/file/IGS_2015_submission_9.pdf

Éditeur(s) : HAL CCSD
Résumé : International audience
We propose an algorithm based on a model of visual perception that is meant to reflect the human judgment about the similarity of handwritten samples. The algorithm builds upon the Fuzzy Feature Contrast model and proposes an implementation of such a model in the domain of handwriting. The algorithm has been validated on the RIMES dataset, by comparing its performance with those of a panel of human experts. The experimental results show that the performance of the proposed algorithm is almost indistinguishable from the expert one and therefore may be a viable tool for handwriting comparison.
17th Biennial Conference of the International Graphonomics Society
Pointe-à-Pitre, Guadeloupe

hal-01165766
https://hal.univ-antilles.fr/hal-01165766
https://hal.univ-antilles.fr/hal-01165766/document
https://hal.univ-antilles.fr/hal-01165766/file/IGS_2015_submission_5.pdf

Éditeur(s) : HAL CCSD
Résumé : International audience
The goal of our experiment is to develop a useful and accessible tool that can be used to evaluate a patient's health by analyzing handwritten strokes. We use a cloud computing approach to analyze stroke data sampled on a commercial tablet working on the Android platform and a distant server to perform complex calculations using the Delta and Sigma lognormal algorithms. A Google Drive account is used to store the data and to ease the development of the project. The communication between the tablet, the cloud and the server is encrypted to ensure biomedical information confidentiality. Highly parameterized biomedical tests are implemented on the tablet as well as a free drawing test to evaluate the validity of the data acquired by the first test compared to the second one. A blurred shape model descriptor pattern recognition algorithm is used to classify the data obtained by the free drawing test. The functions presented in this paper are still currently under development and other improvements are needed before launching the application in the public domain.
17th Biennial Conference of the International Graphonomics Society
Pointe-à-Pitre, Guadeloupe

hal-01165890
https://hal.univ-antilles.fr/hal-01165890
https://hal.univ-antilles.fr/hal-01165890/document
https://hal.univ-antilles.fr/hal-01165890/file/IGS_2015_submission_20.pdf

Éditeur(s) : HAL CCSD
Résumé : International audience
Identifying the writer of a document establishes its authenticity or authorship and has several applications, notably in forensic and historical document analysis. Previous research has shown the potential of Interest Points (IP) for writer identification, but existing methods require segmentation or training. This paper evaluates the performance of intuitive features computed directly from IP properties rather than extracting descriptors at their locations; allowing for a training-free approach. Secondly, we show that adapting detectors to the specific task of writer identification is not only vital for performance but also allows for segmentation-free approaches. Experiments on widely-used datasets show the potential of the method applied self-contained and when combined with existing methods. Limitations of our method relate to the amount of data needed in order to obtain reliable models.
17th Biennial Conference of the International Graphonomics Society
Pointe-à-Pitre, Guadeloupe

hal-01165881
https://hal.univ-antilles.fr/hal-01165881
https://hal.univ-antilles.fr/hal-01165881/document
https://hal.univ-antilles.fr/hal-01165881/file/IGS_2015_submission_15.pdf

Éditeur(s) : HAL CCSD
Résumé : International audience
Indic scripts are among few scripts in the world that have had continuous development for more than two millennia. The modern forms of the scripts are the result of infinitesimal changes in handwriting being accumulated over centuries. They present us with a unique opportunity to understand various changes occurring in handwriting behavior. We have taken four major Indic scripts in six different stages of evolution and extracted features quantifying their handwriting behavior. We have derived these features by applying the principles of handwriting production and gesture analysis on a paleographic data set. We present various trends and behaviors that occurred during script development and discuss our interpretation of the results in terms of evolution of handwriting behavior. We then briefly discuss the detailed analyses that will be performed on the dataset in the future. We also consider the applications of these results in digital paleography and handwriting-driven systems.
17th Biennial Conference of the International Graphonomics Society
Pointe-à-Pitre, Guadeloupe

hal-01165770
https://hal.univ-antilles.fr/hal-01165770
https://hal.univ-antilles.fr/hal-01165770/document
https://hal.univ-antilles.fr/hal-01165770/file/IGS_2015_submission_8.pdf

Éditeur(s) : HAL CCSD
Résumé : International audience
The large majority of methods proposed in literature for handwriting recognition assume that words are produced drawing large parts of the ink without lifting the pen, other than horizontal bars and dots. This fundamental assumption, however, does not always hold: while some educational systems provide explicit training for producing continuous handwriting, minimizing the number of pen-up during the production of a word, others do not. As a consequence, whenever the handwriting presents pen-up within a word, the recognition performance can drop significantly. In a preliminary study, we presented an algorithm for discriminating among different types of ink appearing in handwriting, namely isolated characters, cursive, dots, horizontal and vertical bars, based on the use of a suitable set of features. In this paper, we have characterized the discriminative power of each considered feature according to different measures and we have proposed a method for combining the different feature rankings. We have also used the Fischer's Linear Discriminant Analysis (LDA) for exhaustively selecting the best feature subsets with increasing number of features. Finally, we have compared the results obtained by using the feature subsets provided by LDA with those obtained with the feature subsets selected according to our feature ranking. The experimental results, on different datasets of handwritten words, showed that our approach successfully achieves its aim allowing to reduce the computational cost without affecting the overall performance of the recognition process.
17th Biennial Conference of the International Graphonomics Society
Pointe-à-Pitre, Guadeloupe

hal-01165877
https://hal.univ-antilles.fr/hal-01165877
https://hal.univ-antilles.fr/hal-01165877/document
https://hal.univ-antilles.fr/hal-01165877/file/IGS_2015_submission_13.pdf