Paper Info
Title
Stroke-Based Performance Metrics for Handwritten Mathematical Expressions
Abstract
Evaluating mathematical expression recognition involves a complex interaction of input primitives (e.g. pen/finger strokes), recognized symbols, and recognized spatial structure. Existing performance metrics simplify this problem by separating the assessment of spatial structure from the assessment of symbol segmentation and classification. These metrics do not characterize the overall accuracy of a pen-based mathematics recognition, making it difficult to compare math recognition algorithms, and preventing the use of machine learning algorithms requiring a criterion function characterizing overall system performance. To address this problem, we introduce performance metrics that bridge the gap from handwritten strokes to spatial structure. Our metrics are computed using bipartite graphs that represent classification, segmentation and spatial structure at the stroke level. Overall correctness of an expression is measured by counting the number of relabelings of nodes and edges needed to make the bipartite graph for a recognition result match the bipartite graph for ground truth. This metric may also be used with other primitive types (e.g. image pixels).
Year
DOI
Venue
2011
10.1109/ICDAR.2011.75
ICDAR-1
Keywords
Field
DocType
graph theory,handwritten character recognition,mathematics computing,bipartite graphs,handwritten mathematical expressions,handwritten strokes,input primitives,math recognition algorithms,mathematical expression recognition,pen-based mathematics recognition,recognized spatial structure,recognized symbols,spatial structure assessment,stroke level segmentation,stroke-based performance metrics,symbol classification,symbol segmentation,Graphics Recognition,Handwriting Recognition,Math Recognition,Performance Evaluation
Graph theory,Computer vision,Expression (mathematics),Pattern recognition,Segmentation,Computer science,Correctness,Bipartite graph,Handwriting recognition,Ground truth,Artificial intelligence,Pixel
Conference
ISSN
Citations 
PageRank 
1520-5363
11
0.51
References 
Authors
5
5
Name
Order
Citations
PageRank
Richard Zanibbi145238.74
Amit Pillay2110.51
Harold Mouchere31029.22
Christian Viard-Gaudin444446.20
Dorothea Blostein581069.76