Handwritten/Machine-printed and Arabic/Latin Mathematical Formula Discrimination and Recognition - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

Handwritten/Machine-printed and Arabic/Latin Mathematical Formula Discrimination and Recognition

Résumé

In this paper we mainly introduce a method for mathematical formula script and type identification based on handcrafted features. Arabic/Latin scripts are discriminated by detecting specific symbols based on their pixel density and distribution. Once the formula script identified, we proposed to separate between machine-printed and handwritten formulas. For that, we analyzed the spaces between some specific symbols and their neighbors and the pixel density of some other symbols presenting discriminative differences in their form when they are handwritten or machine-printed. The use of such structural characteristics makes the complexity of the method considerably lower than learning based methods. To finally recognize formulas, two main steps are followed: symbol recognition and formula structure analysis. For the first step, we used a combination of statistical features and an instance-based classifier. For the second step, we proceeded by top-down and bottom-up parsing scheme based on operator dominance. A set of replacement rules is defined by a coordinate grammar. Formula parsing consists of applying, from the dominant operator and its context, the appropriate rule to divide the formula into sub-formulas which will be recursively analyzed by the same way. Carried experiments on various mathematical formulas, show the efficiency of both script and type identification and recognition proposed methods.
Fichier principal
Vignette du fichier
Kawther-paper.pdf (291.11 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01981545 , version 1 (15-01-2019)

Identifiants

  • HAL Id : hal-01981545 , version 1

Citer

Kawther Khazri Ayeb, Afef Kacem Echi. Handwritten/Machine-printed and Arabic/Latin Mathematical Formula Discrimination and Recognition. International Workshop on Arabic Script Analysis and Recognition, Apr 2017, NANCY, France. ⟨hal-01981545⟩
79 Consultations
82 Téléchargements

Partager

Gmail Facebook X LinkedIn More