A* Path Planning for Line Segmentation of Handwritten Documents

Applied Sciences

We present a learning-free method for text line segmentation of historical handwritten document images. This method relies on automatic scale selection together with second derivative of anisotropic Gaussian filters to detect the blob lines that strike through the text lines. Detected blob lines guide an energy minimization procedure to extract the text lines. Historical handwritten documents contain noise, heterogeneous text line heights, skews and touching characters among text lines. Automatic scale selection allows for automatic adaption to the heterogeneous nature of handwritten text lines in case the character height range is correctly estimated. In the extraction phase, the method can accurately split the touching characters among the text lines. We provide results investigating various settings and compare the model with recent learning-free and learning-based methods on the cBAD competition dataset.

Journal of Information Systems, Operations Management, 2013

Identification of text lines in documents, or text line segmentation, represents the first step in the process called ‘Text recognition”, whose purpose is to extract the text and put it in a more understandable format. The paper proposes a seam carving algorithm as an approach to find the text lines. This algorithm uses a new method that allocates dynamic weights for every processed pixel in the original image. With this addition, the resulting lines follow the text more accurately. The downside of this technique is the computational time overhead

—Text-line extraction in handwritten documents is an important step for document image understanding, and a number of algorithms have been proposed to address this problem. In order to overcome this limitation, we develop text-line extraction algorithm for cursive handwriting. Our method is based on connected components (CCs), however, unlike conventional methods, we analysed strokes and partition under-segmented CCs into normalized ones. Due to this normalization, the proposed method is able to estimate the states of CCs for a range of different languages and writing styles. I. INTRODUCTION TEXT-LINE extraction in document images is an essential step for various document image processing tasks such as layout analysis and optical character recognition (OCR).Therefore, there have been a lot of researches in this area, and a number of algorithms have been proposed for the extraction of text-lines in machine-printed document images. However, text-line extraction in handwritten documents is still considered a challenging problem: the scale and orientation of characters are spatially varying, inter-line distances are irregular, and characters may touch across words and/or text-lines. Handwriting detection is a technique or ability of computer to receive & interpret intelligible handwritten input from source. Handwriting recognition is comparatively difficult, because different people have different handwriting style. In optical character recognition, segmentation is a significant phase and accuracy of character recognition highly depends on accuracy of segmentation. Incorrect segmentation leads to incorrect character recognition. Segmentation phase includes text line, word, and character segmentation. Text line detection and separation in digital image documents is a challenging job for handwritten document analysis and character recognition. The problem becomes compounded if the text lines in the text image are connected or overlapped. Emergence of these problems is common in handwritten documents in comparison of printed documents because of individual's varying handwriting styles. Researchers are continuously working on these problems for different languages. Text-line extraction in handwritten documents is an important step for document image understanding, we develop a language-independent text-line extraction algorithm. However, most conventional work focused on specific character sets. That is, conventional algorithms address the variations caused by individual writers by exploiting language-specific features. The situation is worse for Indian scripts where most characters are connected. On the other hand, character components are placed in a one-dimensional way in cursive Latin-based and Indian scripts, allowing us to develop horizontal bottom-up clustering rules. Our method is based on connected components (CCs), however, unlike conventional methods; we analyze strokes and partition under-segmented CCs into normalized ones. Due to this normalization, the proposed method is able to estimate the states of CCs for a range of different languages and writing styles. From the estimated states, we build a cost function whose minimization yields text-lines. We develop an effective CC segmentation method: by partitioning under-segmented CCs into normalized ones, we can estimate states reliably in a variety of documents.

International Journal on Document Analysis and Recognition (IJDAR), 2014

Text line segmentation in handwritten documents is an important task in the recognition of historical documents. Handwritten document images contain text-lines with multiple orientations, touching and overlapping characters between consecutive text-lines and different document structures making line segmentation a difficult task. In this paper we present a new approach for handwritten text line segmentation solving the problems of touching components, curvilinear text lines and horizontally-overlapping components. The proposed algorithm formulates line segmentation as finding the central path in the area between two consecutive lines. This is solved as a graph traversal problem. A graph is constructed using the skeleton of the image. Then, a path-finding algorithm is used to find the optimum path between text lines. The proposed algorithm has been evaluated on a comprehensive dataset consisting of five databases: ICDAR2009, ICDAR2013, UMD, the George Washington and the Barcelona Marriages Database. The proposed method outperforms the state of the art considering the different types and difficulties of the benchmarking data.

2018 16th International Conference on Frontiers in Handwriting Recognition (ICFHR)

Text line segmentation in handwritten document image, as one of the preliminarily steps for document image recognition, is a challenging problem. In this paper, a hybrid method for text line extraction in handwritten document images is presented. Initially, a connected component (CC) labelling method following by a CC filtering is employed to extract a set of CCs from the input document image. A new distance measure is introduced to compute normal distances between the extracted CCs. By traversing the normal distance matrix from both the right and left directions, halfchains of CCs are constructed. The CCs half-chains are merged to obtain CCs full-chains. From the extracted fullchains separator lines are obtained. A gradient metric is proposed to detect and remove touching text lines. Using remaining separator lines the adaptive projection profile of the image is computed. Based on the projection profile, coarse text line extraction is performed. Finally, a fine text lines extraction is performed by applying a postprocessing step. To evaluate the method, two benchmarks named ICDAR2013 handwriting segmentation contest, and Kannada datasets composed of handwritten document images in English, Greek, Bengali, and Kannada languages were considered for experimentation. Experimental results indicate a promising performance was obtained compared to some of the state-of-the-art methods.

Text-line segmentation of unconstrained handwritten document is a difficult task because of variation in inter-line distance and base-line skew. Overlapping and touching problems, which frequently happen between two consecutive text-lines in unconstrained handwritten text documents, significantly increase complexities of text-line segmentation. In this paper we propose a novel approach based on painting technique to make foreground and background painted and smooth separately. Morphological operation (dilation) is employed on the foreground portion of the painted and smooth image to dilate it and get each line as a single component. Thinning operation on the background portion of the dilated image followed by some trimming operations are performed to get some candidate lines. By using the starting and end points information of all the candidate lines and distance analysis amoung them corresponding lines with minimum distnce are connected to gether to segment text-lines. We tested the proposed scheme on text pages of different scripts such as Persian, English, French, German, Greek, Bangla, Oriya, Kannada and we obtained encouraging results.

2014

Preprocessing of document image is a very important step to handle the deformations namely noise, different handwriting complexities that may result in base line skew, word skew, character skew, accents may be cited either above or below the text line and parts of neighboring text lines may be connected, etc. The paper proposes a novel preprocessing technique for handwritten document to handle some of the deformations usually present in the document like touching components, overlapping components, skewed lines, words with individual skews etc. and build a proper text image with all these deformations removed. Based on the analysis of Indian script character shapes and literature survey, it proposes a new sequence of preprocessing methods. A binarized image is sub-sampled and connected components are extracted. These components are dilated and thinned and is given to Hough transform for both global skew and local skew detection for line extraction. The word segmentation is done with...

2008

This paper addresses the problem of automatic text-line and word segmentation in handwritten document images. Two novel approaches are presented, one for each task. In textline segmentation a Viterbi algorithm is proposed while an SVM-based metric is adopted to locate words in each textline. The overall algorithm tested in ICDAR2007 Handwriting Segmentation Contest showing highly promising results.

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.

Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods, 2017

Tracking of objects in videos consists of giving a label to the same object moving in different frames. This labelling is performed by predicting position of the object given its set of features observed in previous frames. In this work, we apply the same rationale by considering each connected component in the manuscript as a moving object and to track it so that to minimize the distance and angle of of the connected component to its nearest neighbour. The approach was applied to images of ICDAR 2013 handwritten segmentation contest and proved to be robust against text orientation, size and writing script.

International Journal Of Computers Communications & Control (IJCCC), 2014

The first step in the text recognition process is represented by the text line segmentation procedures. Only after text lines are correctly identified can the process proceed to the recognition of individual characters. This paper proposes a line segmentation algorithm based on the computation of an information content level, called energy, for each pixel of the image and using it to execute the seam carving procedure. The algorithm proposes the identification of text lines which follow the text more accurately with the expected downside of the computational overhead.

… Analysis for Libraries, 2006. DIAL'06 …, 2006

We present an approach to finding (and separating) lines of text in free-form handwritten historical document images. After preprocessing, our method uses the count of foreground/background transitions in a binarized image to determine areas of the document that are likely to be text lines. Alternatively, an Adaptive Local Connectivity Map (ALCM) found in the literature can be used for this step of the process. We then use a min-cut/max-flow graph cut algorithm to split up text areas that appear to encompass more than one line of text. After removing text lines containing relatively little text information (or merging them with nearby text lines), we create output images for each line. A grayscale output image is created, as well as a special mask image containing both the foreground and information flagging ambiguous pixels. Foreground pixels that belong to other text lines are removed from the output images to provide cleaner line images useful for further processing. While some refinement is still necessary, the result of early experimentation with our method is encouraging.

2008

In this paper, we present a new text line detection method for handwritten documents. The proposed technique is based on a strategy that consists of three distinct steps. The first step includes image binarization and enhancement, connected component extraction, partitioning of the connected component domain into three spatial sub-domains and average character height estimation. In the second step, a block-based Hough transform is used for the detection of potential text lines while a third step is used to correct possible splitting, to detect text lines that the previous step did not reveal and, finally, to separate vertically connected characters and assign them to text lines. The performance evaluation of the proposed approach is based on a consistent and concrete evaluation methodology.

International Journal of Cognitive Informatics and Natural Intelligence, 2020

In text line segmentation, there are three classes of methods: either by sorting physical units such as pixels or connected components (CC) constituting a line or by searching for the baseline of each word and grouping together those who participate in the same line. The third class analyzes the separation locations between the lines. After an overview of lines segmentation approaches, the authors introduced a new method emphasizing its simplicity, speed, and originality. The proposed approach detects the starting components of the lines in the first step. In the second step, it defines a number of agents that start the segmentation process from their starting points between the starting components of lines. Each agent aims to reach the left edge of the document through the correct path. The algorithm used by the agents is based on the morphological process, characteristics of the Arabic manuscript and a communication system. The experimental results on an Arabic dataset show that t...

Text line segmentation is a major task of handwritten document processing. In this paper we present a method to detect and segment unconstrained handwritten documents written in Hindi and English. Document image is first binarized and connected components are identified. Based on Hough lines the text lines are identified. Skew angle is determined by calculating the slope of the detected line and then the skewness is minimized. Segmentation is then performed and the result is refined by removing the noise which basically comprises components from adjacent lines.