Reconnaissance de l'écriture manuscrite

Résumé

La reconnaissance de l’écriture manuscrite (en anglais, handwritten text recognition ou HTR) est un traitement informatique qui a pour but de traduire un texte écrit en un texte codé numériquement. Il faut distinguer deux reconnaissances distinctes, avec des problématiques et des solutions différentes :

la reconnaissance en-ligne ;

la reconnaissance hors-ligne.

La reconnaissance de l’écriture manuscrite fait appel à la reconnaissance de forme, mais également au traitement automatique du langage naturel. Cela veut dire que le système, tout comme le cerveau humain, reconnaît des mots et des phrases existant dans un langage connu plutôt qu’une succession de caractères. Ceci améliore grandement la robustesse. Reconnaissance hors-ligne La reconnaissance hors-ligne travaille sur un instantané d’encre numérique (sur une image). C’est le cas notamment de la reconnaissance optique de caractères. Dans ce contexte, il est impossible de savoir comment ont été tracés les diffé

Source officielle

https://fr.wikipedia.org/wiki/Reconnaissance_de_l'%C3%A9criture_manuscrite

À propos de ce résultat

Cette page est générée automatiquement et peut contenir des informations qui ne sont pas correctes, complètes, à jour ou pertinentes par rapport à votre recherche. Il en va de même pour toutes les autres pages de ce site. Veillez à vérifier les informations auprès des sources officielles de l'EPFL.

Publications associées (80)

Chargement

Afficher plus

Publications associées

Chargement

Personnes associées (14)

Personnes associées

Chargement

Unités associées (10)

Unités associées

Chargement

Concepts associés (27)

Concepts associés

Chargement

Cours associés (8)

Cours associés

Chargement

Séances de cours associées (8)

Séances de cours associées

Chargement

Publications associées (80)

ICFHR2014 Competition on Arabic Writer Identification Using AHTID/MW and KHATT Databases

Fouad Slimane

This paper describes the first edition of the Arabic writer identification competition using AHTID/MW and KHATT databases held in the context of the 14th International Conference on Frontiers in Handwriting Recognition (ICFHR2014). This competition has used the new freely available Arabic Handwritten Text Images Database written by Multiple Writers (AHTID/MW) and the Arabic handwritten text database called KHATT presented in ICFHR2012. We propose three tasks in this Arabic writer identification competition: the first and second are based respectively on word and text line level using the AHTID/MW database and the third one is paragraph based using the KHATT database. We received one system for the second task, three systems for the third task and none for the first task. All systems are tested in a blind manner using a set of images kept internal. A short description of the participating groups, their systems, the experimental setup, and the observed results are presented.

2014

Chargement

We introduce a method for automated grading of handwritten essays written by foreign language learners of French. The handwriting recognition system allows digitising the essays for further processing and functions at a low character error rate. The transcriptions are then vectorised using embeddings from state-of-the-art pre-trained natural language processing models. On top of the extracted word-level features, a deep recurrent network was trained for grade predictions for essays, using the nine different grading criteria as target variables. Scores on these criteria were previously obtained from human expert raters for more than 6’000 student essays. We present preliminary findings on prediction accuracy and discuss possible future developments and applications of the system.

2020

Chargement

Workflow Monitoring based on Multi-view Reconstruction

Daniel Weinland

Activity recognition has primarily addressed the identification of either actions or well-defined interactions among objects in a scene. In this work, we extend the scope to the study of workflow monitoring. In a workflow, ordered groups of activities (phases) with different durations take place in a constrained environment and create temporal patterns across the workflow instances. We address the problem of recognizing phases, based on exemplary recordings. We propose to use Workflow-HMMs, a form of HMMs augmented with phase probability variables that model the complete workflow process. This model takes into account the full temporal context which improves on-line recognition of the phases, especially in case of partial labeling. Targeted applications are workflow monitoring in hospitals and factories, where common action recognition approaches are difficult to apply. To avoid interfering with the normal workflow, we capture the activity of a room with a multiple-camera system. Additionally, we propose to rely on real-time low-level features (3D motion flow) to maintain a generic approach. We demonstrate our methods on sequences from medical procedures performed in a mock-up operating room. The sequences follow a complex workflow, containing various alternatives.

2009

Chargement

Afficher plus