A Robust Thinning Algorithm for Straightening of Curved Text Line

There are more than 1000 languages and 14 scripts used by 112 million people in India. All of these scripts divide the document in three parts: Text block, Image block, and Table block. In 21st century, there is a need, obvious reasons, to convert these old printed documents in digital form. Converting them manually is a huge and difficult task. Further it is prone to human errors. Another automated technique is to use Optical character recognition (OCR) system to convert the entire printed document image into editable document. In this paper, an effort has been made to develop OCR technique which converts the printed document into editable document. Firstly a scanned document is preprocessed for noise and skew correction. It is then followed by text-non text classification. Then text line detection has to be performed in the text area. There is no method available which can detect the text line if the image contains the multicolumn text area. In this paper the main contribution is to detect the blocks and detect the text lines in these detected blocks. The technique which can extract the text lines in image document is presented here. After extraction of text lines, word segmentation, character segmentation, and template matching can be performed.

Extraction of text lines from handwritten/printed document images is one of the important steps in the process of an Optical Character Recognition (OCR) system. In case of handwritten document images, presence of skewed, touching or overlapping text line(s) makes this process a real challenge to the researcher. In the present work, a new text line extraction technique based on line contour estimation is reported. Here, digitized document image is initially partitioned into a number of vertical fragments of equal width. Then all the line segments present in these vertical fragments are detected. Finally, the neighboring line segments are analyzed to place them inside the line boundary in which they actually belong. For experimental purpose, the developed technique is tested on CMATERdb1.2.1 database and present technique extracts 88.44% text lines successfully.

Text line extraction from complex handwritten documents, especially for historical collections, is still an unsolved problem. There is a strong demand for reliable and robust approaches since text line extraction is a crucial pre-processing step for modern text recognition and keyword spotting systems. We propose a binarization-free system which employs a newly developed clustering approach based on so-called 'superpixels'. Although multiple ways of generating superpixels were developed in the past, we demonstrate that even a standard method yields impressive results. Our clustering approach is applicable to various scenarios by making use of general characteristics of text lines (e.g., curvilinearity, interline spacings, local homogeneity), and without adapting its parametrization. State-of-the-art results are achieved by the same parametrization for 8 different well-established benchmarking datasets. These datasets cover historical and modern texts as well as images with diverse resolutions and fonts. The system is developed for detecting text lines in complex scenarios. It is not tuned to assign foreground pixels to detected text lines. Thus, superior performance is achieved for the historical datasets for which no pixel hit accuracy of 95% is required. Remarkably, for the dataset of the ICDAR 2015 Competition on Text Line Detection in Historical Documents, the average cost per text line was reduced from 9.77 (winning team) to 8.19.

We present a novel approach for the extraction of text lines in handwritten documents using a Convolutional Neural Network to label document image patches as text lines or separators. We first process the document to identify the most suitable patch size on the basis of an overall text line distance estimation. Using this information, we then extract several patches to train the CNN model. Finally, we use the trained model to segment text lines. We have evaluated this technique on the public database Saint Gall and on a private collection provided by the Ancestry company.

Text line extraction from multi-skewed handwritten documents

There are printed artistic documents where text lines of a single page may not be parallel to each other. These text lines may have different orientations or the text lines may be curved shapes. For the optical character recognition (OCR) of these documents, we need to extract such lines properly. In this paper, we propose a novel scheme, mainly based on the concept of water reservoir analogy, to extract individual text lines from printed Indian documents containing multioriented and/or curve text lines. A reservoir is a metaphor to illustrate the cavity region of a character where water can be stored. In the proposed scheme, at first, connected components are labeled and identified either as isolated or touching. Next, each touching component is classified either straight type (S-type) or curve type (C-type), depending on the reservoir base-area and envelope points of the component. Based on the type (S-type or C-type) of a component two candidate points are computed from each touching component. Finally, candidate regions (neighborhoods of the candidate points) of the candidate points of each component are detected and after analyzing these candidate regions, components are grouped to get individual text lines.

Text detection in natural scene images is a challenging problem in computer vision. To robust detect various texts in complex scenes, a hierarchical recursive text detection method is proposed in this paper. Usually, texts in natural scenes are not alone and arranged into lines for easy reading. To find all possible text lines in an image, candidate text lines are obtained using text edge box and conventional neural network at first. Then, to accurately find out the true text lines in the image, these candidate text lines are analyzed in a hierarchical recursive architecture. For each of them, connected components segmentation and hierarchical random field based analysis are recursively employed until the detected text line no more changes. Now the detected text lines are output as the text detection result. Experiments on ICDAR 2003 dataset, ICDAR 2013 dataset and Street View Dataset show that the hierarchical recursive architecture can improve text detection performance and the proposed method achieves the state-of-art in scene text detection.

Handwritten Chinese envelopes have three obvious characteristics: handwritten text lines are the main part of the envelope image; there is no distinct border between the destination address block (DAB) and sender address block (SAB); and handwritten Chinese characters are composed of complicated strokes with more freedom. A method for segmenting the envelope image into several candidate DABs and selecting the best one as the DAB is not yet suitable for handwritten Chinese envelopes. This paper presents a new method of DAB location on envelopes based on extraction of text lines, according to the characteristics of handwritten Chinese envelopes. Our method divides the DAB location problem into several simpler sub-problems and solves them respectively. Experimental results of extraction rate for DAB and average processing time on 500 samples directly sampled from mail sorting machines shows that this method is effective and takes less CPU time.

Text line extraction is one of the critical steps in document analysis and optical character recognition (OCR) systems. The purpose of this study is to address the problem of text line extraction of ancient Thai manuscripts written on palm leaves, using an Adaptive Partial Projection (APP) technique by integrating a modified partial projection and smooth histogram with recursion. The proposed approach was compared with a Modified Partial Projection (MPP) looking at vowel analysis and touching components of two consecutive lines. The results from this research suggested that the proposed approach for practical data on palm leaf manuscripts has better performance in solving the line segmentation problem.

This paper proposes a character segmentation and retrieval method for a learning support system that analyzes digitized Japanese historical woodblock printed books. The proposed system detects text lines, segments characters, and retrieves similar characters from document images. The process includes background separation, text line extraction, rule-based character integration and segmentation, and similar character retrieval. The experimental results show that the proposed method segmented all text lines correctly and successfully extracted more than 79% of the complicated characters, as well as provided promising character retrieval results.

This paper describes a text-line extraction based method. The typical segmentation for a printed binary document is based on the horizontal projection analysis and then the regrouping of the connected components. These techniques can't be used for handwritten unconstrained text because data frequently contain undulations and shifts in the baseline, baseline-skew variability and inter-line distance variability. So, we think that the border line for a handwritten unconstrained documents should be a collection of horizontal line segments. From this point of view, we use a partial contour following based method to detect the separating lines. In the current version of our algorithm, we proceed to text slant detection, text line number evaluation by using partial projection. Then we carry out a partial contour following of every line; first in the direction of the writing, then in the opposite direction. After the treatment, the adjacent lines are separated. In the experimental session, we describe the application of the algorithm used for the extraction of text line. Database images contains about one hundred handwritten Arabic texts written by different writers. Results about diacritical points affectation are also reported.

This paper presents document recognition strategies for an important application: Recognition of text document containing multiple lines of text data. A project to study the feasibility of recognizing essays written by middle school students is the focus of the second study. In this project, a scanned document is processed to extract individual lines of text from the essay, extract individual words from the line and then apply word recognition techniques to the extracted words. While individual lines of data are extracted accurately using gap information between lines, extraction of words is a much bigger challenge. Since the essays are written by middle school children, word boundaries are ambiguous, especially when words are written in a non-cursive discrete style. In these cases the gaps between words are sometimes smaller than the gaps between characters of the word causing errors in estimating the location of word boundaries. In this paper, we propose two classes of word boundaries: 1) strong boundaries due to large gaps between words, 2) weak boundaries due to small gaps between words. There are also cases when two words do not have a clear gap between them, but are rather joined to give the appearance of a single word. Results obtained from our phase 1 study will be presented in the paper.

The purpose of this survey is to provide a comprehensive overview of recent advancements in text line segmentation and baseline detection techniques within the analysis of historical document images. Text line extraction is an essential step in the historical documents image analysis pipeline, as its results significantly impact the accuracy of subsequent processes, such as handwritten text recognition (HTR). Through a multi-stage procedure, we carefully selected 49 peer-reviewed studies published since 2019. Based on careful analysis of these studies, we summarize the information of the existing datasets, describe and categorize different methods, and summarize evaluation protocols. In addition, we compare the results of various methods on benchmark datasets. Finally, we highlight the gaps and suggest directions for future research. We believe that this comprehensive survey will be of great assistance to researchers working in the field of historical document image analysis, as it offers critical insights into the latest advancements and developments, providing a foundation for future research.

Scene texts refer to arbitrary text found in images captured by cameras in real-world settings. The tasks of text detection and recognition are critical components of computer vision, with applications spanning scene understanding, information retrieval, robotics, and autonomous driving. Despite significant advancements in deep learning methods, achieving accurate text detection and recognition in complex images remains a formidable challenge for robust real-world applications. Several factors contribute to these challenges. First, the diversity of text shapes, fonts, colors, and styles complicates detection efforts. Second, the myriad combinations of characters, often with unstable attributes, make complete detection difficult, especially when background interruptions obscure character strokes and shapes. Finally, effective coordination of multiple sub-tasks in end-to-end learning is essential for success. This research aimed to tackle these challenges by enhancing text discriminative representation. This study focused on two interconnected problems: Scene Text Recognition (STR), which involves recognizing text from scene images, and Scene Text Detection (STD), which entails simultaneously detecting and recognizing multiple texts within those images. This research focuses on implementing and evaluating the Efficient and Accurate Scene Text Detector (EAST) algorithm for text detection and recognition in natural scene images. The study aims to compare the performance of three prominent Optical Character Recognition (OCR) techniques—TesseractOCR, PaddleOCR, and EasyOCR. The EAST model was applied to a series of sample test images, and the results were visually represented with bounding boxes highlighting the detected text regions. The inference times for each image were recorded, highlighting the algorithm's efficiency, with average times of 0.446, 0.439, and 0.440 seconds for the respective test images. These results indicate that the EAST algorithm is accurate and operates in real-time, making it suitable for applications requiring immediate text recognition.

This article presents a methodology to automate linear feature generalization from image data using a length-preserving thinning algorithm. Conventional thinning algorithms on raster data produce erroneous skeletons at the river edges in the estuary of a river and in the perimeter of the input data. A river skeleton should be connected to the sea through the centre line of an estuary. A related problem is that of shortened skeletons resulting from the boundary-peeling process. This article proposes a length-preserving thinning (LEPT) algorithm that consists of edge-finding, boundary-peeling, skeleton-growth, and noise-removal procedures. The edge-finding procedure finds the edges of a river and the sea and extends the perimeter of the input data by one pixel, thus removing skeleton errors at the edges in the estuary and the perimeter. The boundary-peeling procedure produces a shortened skeleton. The skeleton-growth procedure extends a shortened skeleton to the original river edge based on the direction of the skeleton. The noise-removal procedure removes isolated water spots. This novel thinning algorithm has been applied here to extract a skeleton of the Pascagoula River in Mississippi.