Recognizing handwritten Arabic script through efficient skeleton-based grapheme segmentation algorithm

Abstract

To recognize unlimited set of handwritten Arabic words, an efficient segmentation algorithm is needed to segment these cursive words into a limited set of primal graphemes. We propose a rule-based segmentation algorithm that segments cursive words into graphemes through collecting special feature points from the word skeleton. The development of this algorithm is motivated by the need to solve problems and limitations available in the state-of-the-art algorithms in this area. The preliminary evaluation of the proposed algorithm is promising with over 96% accuracy on a sample subset of the IFN/ENIT database.

A Novel Similar Character Discrimination Method for Online Handwritten Urdu Character Recognition in Half Forms

“…We are also working on segmentation of characters from ligatures and will be reported in future. A related work on segmentation of handwritten Arabic text can be found at [51] that presents an efficient skeleton-based grapheme segmentation algorithm. With some modifications, this segmentation algorithm along with our proposed methodology may serve as a full system for online Urdu handwriting recognition.…”

An Efficient Character Segmentation Algorithm for Offline Handwritten Uighur Scripts Based on Grapheme Analysis

“…Character segmentation techniques available in the present literatures usually split the word image vertically along the cutoff points [7][8][9][10][11][12]. Uighur handwriting has many dot and affix strokes, and their writing positions more casual (for example characters: " ", " ", " ", " ", " "etc.).…”

“…In the existing literature, most of handwriting recognition studies for cursive writings have been devoted to Arabic and Farsi [2][3][4][5][6][7][8][9][10][11][12]. But very less research efforts have been done for Uighur scripts [13][14].…”

“…The former approaches dealt with the word image as a whole unit for recognition [3][4][5][6], while the latter first segmented word into a sequence of characters and recognized them separately [7][8][9][10][11][12]. The segmentation-driven approaches were more favorable for large-scale classification.…”

“…The typical cursive character segmentation approaches were usually based on image analysis, with several important features including projection histogram [7,[9][10], contour feature [8,11] and skeleton feature [12]. Uighur characters have more complex dots and diacritics than Arabic, thus above techniques developed for Arabic handwriting could not be directly implemented in Uighur recognition.…”