Knowledge-Based Baseline Detection and Optimal Thresholding for Words Segmentation in Efficient Pre-Processing of Handwritten Arabic Text

Techniques on detecting baseline and segmenting words in handwritten Arabic text are presented in this paper. Instead of using pure projection, knowledge of the location of the baseline is utilized for accurate baseline detection. Then, distances between words and subwords are respectively analyzed,...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: AlKhateeb, J.H., Jinchang Ren, Ipson, S.S., Jianmin Jiang
Format: Tagungsbericht
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Techniques on detecting baseline and segmenting words in handwritten Arabic text are presented in this paper. Instead of using pure projection, knowledge of the location of the baseline is utilized for accurate baseline detection. Then, distances between words and subwords are respectively analyzed, and their statistical distributions are obtained to decide an optimal threshold in segmenting words. Results on IFN/ENIT database have validated our methods in terms of improved baseline detection and words segmentation for further recognition.
DOI:10.1109/ITNG.2008.71