A Steerable Directional Local Profile Technique for Extraction of Handwritten Arabic Text Lines

Abstract

In this paper, we present a new text line extraction method for handwritten Arabic documents. The proposed technique is based on a generalized adaptive local connectivity map (ALCM) using a steerable directional filter. The algorithm is designed to solve the particularly complex problems seen in handwritten documents such as fluctuating, touching or crossing text lines. The proposed algorithm consists of three steps. Firstly, a steerable filter is used to probe and determine foreground intensity along multiple directions at each pixel while generating the ALCM. The ALCM is then binarized using an adaptive thresholding algorithm to get a rough estimate of the location of the text lines. In the second step, connected component analysis is used to classify text and non text patterns in the generated ALCM to refine the location of the text lines. Finally, the text lines are separated by superimposing the text line patterns in the ALCM on the original document image and extracting the connected components covered by the pattern mask. Analysis of experimental results on the DARPA MADCAT Arabic handwritten document data indicate that the method is robust and is capable of correctly isolating handwritten text lines even on challenging document images.

Bag of Visual Words for Word Spotting in Handwritten Documents Based on Curvature Features

“…We segment document images into lines and then into words using robust algorithm [42]. The sample results of segmented word images are shown in Figure 2.…”

“…In the first stage, the document image is segmented into text lines and each text lines are segmented into primitive segments i.e. words using directional local profile technique [42]. The corner keypoints are extracted from word image using Harris-Laplace Corner detector.…”

Text Extraction from Document Images- A Review

“…Shi et al [16] suggested a method based on adaptive local connectivity map (ALCM) using steerable directional filter for extracting handwritten Arabic text. Firstly, steerable filter is applied to the document image and it is converted into ALCM.…”

Segmentation of Arabic Handwritten Documents into Text Lines using Watershed Transform

“…A method was proposed in [9] that uses ALCM algorithm which gives a mask corresponding to text line locations. Then, the text lines are extracted by superimposing the components with text line pattern mask.…”