Segmentation method of offline mathematical symbols

Jakjoud, Widad; Lazrek, Azzeddine

doi:10.1109/icmcs.2011.5945634

Cited by 9 publications

(1 citation statement)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Technique is depend on contour feature that partitioning paths can be grade constructed on contour feature and the ratio of width and height and then touching characters are segmented [10]. The method of contour approach for extracting symbols from the image representing mathematical expression and improve the result by proposing complete segmentation method which treats both of sub-segmentation upon-segmentation problems [11].…”

Section: Historical Backgroundmentioning

confidence: 99%

Handwritten Mathematical Expressions Recognition using Back Propagation Artificial Neural Network

Shinde¹,

Waghulade²

2016

CAE

View full text Add to dashboard Cite

Handwritten mathematical expressions recognition is yet challenging task due to its intricate spatial structure, tangled semantics and 2-dimensional layout of the characters. There is a still room for enhancement in recognition rate. Artificial neural network is superior to disentangle classification problems. In this paper, feedforward back propagation neural network is implemented to achieve both character recognition and mathematical structure recognition with upgrade in effective performance in addition to accuracy of the experimental results including lessen efforts. System proves its potency by recognizing expressions in analysis of math documents.

show abstract

Section: Historical Backgroundmentioning

confidence: 99%