Character Segmentation of Sindhi, an Arabic Style Scripting Language, using Height Profile Vector
Noor Ahmed Shaikh, Ghulam Ali Mallah, Zaffar Ahmed Shaikh · 2009
2 Abstract: In this p aper, a problem of su b-word segmentation of p rinted Sindhi, an Arabic style scripting language, into characters is addressed. Printed or handwritten Sindhi text is cursive in nature. In t he c ursive w riting, mostly t he s ubsequent characters in a word ar e j oined with ea ch ot her. In t he proposed s egmentation al gorithm, first of all, Height Profile V ector (HPV) of thinned primary s troke of a s ub-word i s calculated a nd ana lyzed for the segmentation i nto i ts constituent characters. The number and locations of possible se gmentation points (PSP) are determined. The number of PSPs gives a rough estimation of the number of characters in t he sub-word. The data around the last PSP is f urther a nalyzed t o de termine t he ex act number of charact ers in t he sub -word. As t he ch aracters' set of Sindhi is the s uperset set of Arabic c haracters' set hence the pr oposed s egmentation al gorithm may b e used for t he seg mentation of text written i n other Arabic scripting languages.