Loading [a11y]/accessibility-menu.js
Recognize assyrian cuneiform characters by virtual dataset | IEEE Conference Publication | IEEE Xplore

Recognize assyrian cuneiform characters by virtual dataset


Abstract:

Cuneiform symbols represent a complex problem in pattern recognition, in particular for OCR (optical character recognition) due to challenges related to cuneiform-like ch...Show More

Abstract:

Cuneiform symbols represent a complex problem in pattern recognition, in particular for OCR (optical character recognition) due to challenges related to cuneiform-like character distortion and font heterogeneity. This paper proposes new approaches to recognise Assyrian cuneiform characters using OCR to classify the symbols. as a new way to recognize the Assyrian letters by dealing with symbols of complex character. The dataset utilised consists of 16 patterns to reflect all probabilities associated with each cuneiform symbol related to their shape and directions, assuming each character consists of a set of symbols. Polygon approximation techniques are used to generate feature vectors for the classification tasks. The proposed method obtains classification ratios up to 91% depending on the algorithm used for the feature vector.
Date of Conference: 19-21 December 2017
Date Added to IEEE Xplore: 12 April 2018
ISBN Information:
Electronic ISSN: 2379-4402
Conference Location: Muscat, Oman

References

References is not available for this document.