A Skew Resistant Method for Persian Text Segmentation

ijcte.org

Abstract—In this paper, we propose a novel method for segmentation of online Persian handwriting into the fundamental building blocks of Persian letters. Employing the findings of our previous work to determine the segmentation points of cursive words and applying ...

Proceedings of the Fifth International Conference on Document Analysis and Recognition. ICDAR '99 (Cat. No.PR00318), 1999

In this paper, a range free skew detection technique for machine printed Gurmukhi documents has been presented. This approach can easily be extended to other Indian language scripts such as Devnagri and Bakngla. Most characters in these scripts have horizontal lines at the top called headlines. The characters forming a word are joined at top by headlines, so that the word appears as one single component with headline. The ratio of pixel density above and below the headline of any word in Gurmukhi script is always less than 1. These inherent characteristics of the script have been employed and a new algorithm based on projection profile method has been devised. By inspecting horizontal and vertical projections at different angles in range [0°, 90°], the skew angle of the document in range [-180°, 180°] can be determined. Thus this approach is not limited to any range of skew angle and skewness in any document with orientation portrait or landscape and placed at any angle can easily be detected and removed.

International Journal of Computer Applications Technology and Research

Segmentation approaches, as processes that divide word into smaller parts which contain one letter at most, have important effect on cursive word recognition. While online cursive word recognition became applied technology in Latin and Chinese languages, complex structural features in Arabic-based script made it an important field of study in Persian and Arabic languages. In this paper, by introducing of Standard Persian Handwriting, we proposed a novel approach to segmentation online Persian cursive script based on width of letter's body in Persian language. Results are shown 99.86% accuracy in detection of expected segmentation points, while recognized extra points reduced 93.73% compared to our previous methods.

Pattern Analysis & Applications

Line segmentation from unconstrained handwritten document is a difficult task because of the writing styles of different individuals. Characters of two consecutive text lines may touch or overlap and such touching/overlapping makes the line segmentation task more complex. In this paper, a painting scheme is proposed to facilitate unconstrained handwritten text-line segmentation process. In the proposed scheme, input text page is vertically decomposed into parallel pipe structures called as strip. The width of strips is automatically computed based on the space (gap) between the consecutive lines in each text-page. Each row of a strip is painted by a gray intensity, which is the average intensity value of gray values of all pixels present in that row-strip. The painted strips are then converted into two-tone painting image and using some smoothing operations the two-tone painted image is smoothed. The white/black spaces in each pipe of the smoothed image are analyzed to get a short line of separation, called as Piece-wise Potential Separating Line (PPSL), between two consecutive black spaces. Finally, the PPSLs are concatenated or extended for text-line separation. The proposed method can also handle touching/overlapping cases. To do so, the proposed system initially detects the touching/ overlapping zones and then based on the structural behavior of such zones, they are segmented.

International Journal of Computer Applications, 2012

Text and not-text segmentation and text line extraction from document images are the most challenging problems of information indexing of Arabic document images such as books, technical articles, business letters and faxes in order to successfully process them in systems such as OCR. Researches on Arabic language related to documents digitization have been focusing on word and handwriting recognition. Few approaches have been proposed for layout analysis for Arabic scanned/captured documents. In this paper we present a page segmentation method that deals with the complexity of the Arabic language characteristics and fonts using the combination between two algorithms. The first method is the Run length Smoothing. The second method is the Connected Component Labeling algorithm for text and non-text classification using SVM. The combination of the two methods is based on Anding and Oring operations between the outputs of the two methods based on certain conditions. Then, dynamic horizontal projection based on dynamic updating of the threshold to commensurate with the noise associated with different documents and in between text lines. The performance evaluation is performed using manually generated ground truth representations from a dataset of Arabic document images captured using cameras and a hardware built for this purpose. Evaluation and experimental results demonstrate that the proposed text extraction method is independent from different document size, text size, font, shape, and is robust to Arabic document segmentation and text lines extraction.

Computer Science Department, Faculty of Computer …, 2004

Character segmentation is a crucial step in most Arabic optical text recognition systems. The recognition process depends mainly on the accuracy of the character segmentation. This paper presents a novel adaptive algorithm for the off-line segmentation of printed Arabic text. There are many challenging features in the Arabic writing, for example, it is cursive and characters in a word can take four different shapes. A general rule cannot apply for segmenting all the characters. Hence, we propose an adaptive rule-based segmentation algorithm based on the general structural relationship of the Arabic text. The main rule used is that "most characters start with and end before a T-junction on the baseline." Some other rules are included to take care of the variations in the main rule. Results show the efficiency of the proposed algorithm, where it is found to achieve a segmentation accuracy of 96.5%.

This paper presents, a hybrid method, low-resolution and high-resolution, for Persian page segmentation. In the low-resolution page segmentation, a pyramidal image structure is constructed for multiscale analysis and segments document image to a set of regions. By high-resolution page segmentation, by connected components analysis, each region is segmented to homogeneous regions and identifying them as texts, images, and tables/drawings. The proposed method was experiment with the Persian documents. The result of these tests have shown that the proposed method provide more accurate and speed results.

Character segmentation is an important preprocessing step for text recognition. The size and shape of characters generally play an important role in the process of segmentation. But for any optical character recognition (OCR) system, the presence of touching characters in textual as well handwritten documents further decreases correct segmentation as well as recognition rate drastically. Because one can not control the size and shape of characters in handwritten documents so the segmentation process for the handwritten document is too difficult. We tried to segment handwritten text by proposing some algorithms, which were implemented and have shown encouraging results. Algorithms have been proposed to segment the touching characters. These algorithms have shown a reasonable improvement in segmenting the touching handwritten characters in Gurmukhi script.

Optical Character Recognition (OCR) is an essential part of Document Analysis System. Among few phases of an OCR system, segmentation is an important phase. After preprocessing phase, it is necessary to segment the text into lines, words and characters before the recognition of text. Segmentation is one of the most important and challenging tasks in a handwritten recognition system. Gurmukhi script can be segmented into paragraphs, lines, words and characters. This paper describes a technique for segmentation of handwritten Gurmukhi script documents into lines with the use of strip based projection profile technique, and to segment lines into words using white space and pitch method.

Procedia Computer Science, 2015

Automatic recognition of writing is among the most important axes in the NLP (Natural language processing). Several entities of different areas demonstrated the need in recognition of handwritten Arabic characters; particularly banks check processing, post office for the automation of mail sorting, the insurance for the treatment of forms and many other industries. One of the most important operations in a handwriting recognition system is segmentation. Segmentation of handwritten text is a necessary step in the development of a system of automatic writing recognition. Its goal is to try to extract all areas of the lines of the text, and this operation is made difficult in the case of handwriting, by the presence of irregular gaps or overlap between lines and fluctuations of the guidance of scripture to the horizontal. In this paper, we have developed three approaches of handwritten Arabic text segmentation, then we compared between these three approaches.