Paper Info
Title
Online flowchart understanding by combining max-margin Markov random field with grammatical analysis.
Abstract
Flowcharts are considered in this work as a specific 2D handwritten language where the basic strokes are the terminal symbols of a graphical language governed by a 2D grammar. In this way, they can be regarded as structured objects, and we propose to use a MRF to model them, and to allow assigning a label to each of the strokes. We use structured SVM as learning algorithm, maximizing the margin between true labels and incorrect labels. The model would automatically learn the implicit grammatical information encoded among strokes, which greatly improves the stroke labeling accuracy compared to previous researches that incorporated human prior knowledge of flowchart structure. We further complete the recognition by using grammatical analysis, which finally brings coherence to the whole flowchart recognition by labeling the relations between the detected objects.
Year
DOI
Venue
2017
10.1007/s10032-017-0284-8
IJDAR
Keywords
Field
DocType
Random Forest,Markov Random Field,Conditional Random Field,Handwriting Recognition,Markov Random Field Model
Structured support vector machine,Computer science,Markov random field,Handwriting recognition,Artificial intelligence,Natural language processing,Random forest,Flowchart,Conditional random field,Pattern recognition,Grammar,Coherence (physics),Machine learning
Journal
Volume
Issue
ISSN
20
2
1433-2833
Citations 
PageRank 
References 
1
0.35
29
Authors
4
Name
Order
Citations
PageRank
Chengcheng Wang13110.14
Harold Mouchère210714.46
Aurélie Lemaitre3639.41
Christian Viard-Gaudin444446.20