A Robust Script Identification System for Historical Indian Document Images

Kavitha, S.; Shivakumara, Palaiahnakote; Kumar, G. Hemantha; Tan, Chew Lim

doi:10.22452/mjcs.vol28no4.2

Cited by 12 publications

(1 citation statement)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Handling handwritten documents is more complex due to several reasons like: irregular line, word and character spacing, character style, font and size vary from writer to writer, variations in stroke direction, stroke width. Many works are reported in literature on PSI since last decade ( [4]; [5]; [6]; [7]; [8]; [9]; [10]; [11]; [41]). Among the few available works on HSI, Hochberg et al [12] proposed a pagelevel script identification from few Indian and non-Indian scripts.…”

Section: Handwritten Script Identification -A Quick Surveymentioning

confidence: 99%

Automatic Line-Level Script Identification From Handwritten Document Images - A Region-Wise Classification Framework for Indian Subcontinent

Obaidullah

Halder

Santosh

et al. 2018

MJCS

View full text Add to dashboard Cite

Script identification is a well-studied problem for automatic processing of document images. Several attempts have been made so far, but it is still far ahead from the complete solution. In this paper, an automatic approach for line-level handwritten script identification (HSI), considering eight official Indic scripts namely: Bangla, Devanagari, Kannada, Malayalam, Oriya, Roman, Telugu, and Urdu is proposed. We consider a 148-dimensional feature vector using: image component fractal dimension, structural and visual appearance, directional stroke, interpolation and Gabor energy based texture features. For classification, we divide the whole script dataset based on different regions of India, to study a region-wise classification performance. Experimentation was carried out using the state-of-the-art classifiers: multilayer perceptron (MLP), support vector machine (SVM), random forest (RF), and fuzzy unordered rule induction algorithm (FURIA). Among all, we found that MLP as the best performer in terms of average accuracy of 98.2%, 99.5%, 99.1%, 99.5%, 99.9%, 98%, 98.9% for eight-script, bi-script, eastern, north, south Indian script groups, scripts with 'matra' vs without 'matra', and dravidian vs. non-dravidian groups respectively.

show abstract