Evaluating Structural Pattern Recognition for Handwritten Math via Primitive Label Graphs - CNRS - Centre national de la recherche scientifique Accéder directement au contenu
Communication Dans Un Congrès Proceedings of SPIE, the International Society for Optical Engineering Année : 2013

Evaluating Structural Pattern Recognition for Handwritten Math via Primitive Label Graphs

Richard Zanibbi
  • Fonction : Auteur
  • PersonId : 907998
Harold Mouchère
Christian Viard-Gaudin

Résumé

Currently, structural pattern recognizer evaluations compare graphs of detected structure to target structures (i.e. ground truth) using recognition rates, recall and precision for object segmentation, classification and relationships. In document recognition, these target objects (e.g. symbols) are frequently comprised of multiple primitives (e.g. connected components, or strokes for online handwritten data), but current metrics do not characterize errors at the primitive level, from which object-level structure is obtained. Primitive label graphs are directed graphs defined over primitives and primitive pairs. We define new metrics obtained by Hamming distances over label graphs, which allow classification, segmentation and parsing errors to be characterized separately, or using a single measure. Recall and precision for detected objects may also be computed directly from label graphs. We illustrate the new metrics by comparing a new primitive-level evaluation to the symbol- level evaluation performed for the CROHME 2012 handwritten math recognition competition. A Python-based set of utilities for evaluating, visualizing and translating label graphs is publicly available.
Fichier principal
Vignette du fichier
ZMV_DRR2013.pdf (413.09 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00852866 , version 1 (21-08-2013)

Identifiants

Citer

Richard Zanibbi, Harold Mouchère, Christian Viard-Gaudin. Evaluating Structural Pattern Recognition for Handwritten Math via Primitive Label Graphs. Document Recognition and Retrieval XX, Feb 2013, Burlingame, United States. pp.865817-865817-11, ⟨10.1117/12.2008409⟩. ⟨hal-00852866⟩
355 Consultations
211 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More