DocumentCode :
183314
Title :
Using Off-Line Features and Synthetic Data for On-Line Handwritten Math Symbol Recognition
Author :
Davila, Kenny ; Ludi, Stephanie ; Zanibbi, Richard
Author_Institution :
Dept. of Comput. Sci., Rochester Inst. of Technol., Rochester, NY, USA
fYear :
2014
fDate :
1-4 Sept. 2014
Firstpage :
323
Lastpage :
328
Abstract :
We present an approach for on-line recognition of handwritten math symbols using adaptations of off-line features and synthetic data generation. We compare the performance of our approach using four different classification methods: AdaBoost. M1 with C4.5 decision trees, Random Forests and Support-Vector Machines with linear and Gaussian kernels. Despite the fact that timing information can be extracted from on-line data, our feature set is based on shape description for greater tolerance to variations of the drawing process. Our main datasets come from the Competition on Recognition of Online Handwritten Mathematical Expressions (CROHME) 2012 and 2013. Class representation bias in CROHME datasets is mitigated by generating samples for underrepresented classes using an elastic distortion model. Our results show that generation of synthetic data for underrepresented classes might lead to improvements of the average per-class accuracy. We also tested our system using the Math Brush dataset achieving a top-1 accuracy of 89.87% which is comparable with the best results of other recently published approaches on the same dataset.
Keywords :
feature extraction; handwritten character recognition; image classification; learning (artificial intelligence); mathematics computing; support vector machines; AdaBoost. M1; C4.5 decision trees; Gaussian kernels; classification methods; feature set extraction; off-line features; on-line handwritten math symbol recognition; random forests; support-vector machines; synthetic data generation; Accuracy; Histograms; Kernel; Shape; Support vector machines; Testing; Training; AdaBoost; Elastic Distortion; Handwritten Character Recognition; Off-line Features; Random Forest; SVM;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Frontiers in Handwriting Recognition (ICFHR), 2014 14th International Conference on
Conference_Location :
Heraklion
ISSN :
2167-6445
Print_ISBN :
978-1-4799-4335-7
Type :
conf
DOI :
10.1109/ICFHR.2014.61
Filename :
6981040
Link To Document :
بازگشت