Creating a Handwriting Recognition Corpus for Bushman Languages

Williams, Kyle; Suleman, Hussein

doi:10.1007/978-3-642-24826-9_28

Cited by 3 publications

(2 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A corpus of handwritten |Xam words and their transcriptions was created for use as a dataset in this study [25]. The words in the corpus were binarised and normalised to 64x64 pixel images as part of a preprocessing step [25].…”

Section: Xam Word Corpusmentioning

confidence: 99%

See 1 more Smart Citation

A comparison of machine learning techniques for handwritten |Xam word recognition

Williams

Suleman

Paihama

2013

Proceedings of the South African Institute for Computer Scientists and Information Technologists Conference

Self Cite

View full text Add to dashboard Cite

The Bleek and Lloyd collection contains 19th century handwritten notebooks that document the language and culture of the |Xam-speaking people who lived in Southern Africa. Access to this rich data could be enhanced by transcriptions of the text; however, the complex diacritics used in the notebooks complicate the process of transcription. Machine learning techniques could be used to perform this transcription, but it is not known which techniques would produce the best results. This paper thus reports on a comparison of 3 popular techniques applied to this problem: artificial neural networks (ANN); hidden Markov models (HMM); and support vector machines (SVM). It was found that an SVM-based classifier using histograms of oriented gradients as features resulted in the best word recognition accuracy of 58.4%. Furthermore, it was found that most feature extraction parameters did not have a large effect on recognition accuracy and that the SVM-based recognisers outperform both ANN-and HMM-based recognisers.

show abstract

Section: Xam Word Corpusmentioning

confidence: 99%

“…The words in the corpus were binarised and normalised to 64x64 pixel images as part of a preprocessing step [25]. For word recognition, the task was to recognise each word in its entirety as a single pattern.…”

Section: Xam Word Corpusmentioning

confidence: 99%