Text Lines Research Articles

Text Extraction and Recognition in Natural Scene Images using Contourlet Transform and PNN

Of late, the rapid development in the technology and multimedia capability in digital cameras and mobile devices has led to ever increasing number of images or multi-media data to the digital world. Particularly, in natural scene images, the text content provides explicit information to understand the semantics of images. Therefore, a system developed for extracting and recognizing texts accurately from natural scene images, in real-time, has significant relevance to numerous applications such as, assistive technology for people with vision impairment, tourist with language barrier, vehicle number plate detection, street signs, advertisement bill boards, robotics, etc. The extraction of the texts from natural scene images is a formidable task due to large variations in character fonts, styles, sizes, text orientations, presence of complex backgrounds and varying light conditions. The main focus of this research paper is to propose a novel hybrid approach for automatic detection, localization, extraction and recognition of text in natural scene images with cluttered background. Firstly, image regions with text are detected using edge features (GLCM) extracted from Contourlet transformed image and SVM (Support Vector Machine) classifier. Secondly, horizontal projection is applied on text regions for segmenting lines and vertical projection is applied on each text line for segmenting characters. The proposed method for text extraction has produced the precision, recall, F-Score and accuracy of 98.50%, 90.85.62%, 95.00%, and 89.90%, respectively. And, these results prove that the proposed method is efficient. Further, the so extracted characters are processed for recognition using contourlet transform and Probabilistic Neural Network (PNN) classifier. The computed features are moment invariants. Only the English script is considered for the experimentation. The proposed character recognition method has accuracy of 79.07%, which is higher in comparison to accuracy of 75.15% obtained by KNN (K-Nearest Neighbors) classifier

General Document Image Correction Method Based on Text Line in Natural Scene

This paper presents a general document image correction method based on the text line. The proposed method roughly screens the text area and implements rotation correction based on the TextSnake text detection model. Then by the relative positions of characters, the principle of text direction consistency and the two-way matching strategy, the precise positioning is realized. At last, the information of text ridges is obtained to acquire the nonlinear mapping relationship of the whole graph, Therefore achieving correction reconstruction of the general document image. The experiment results show that the correction method can overall solve image quality problems such as tilt distortion and improve the recognition rate of tilt distortion image.

Automatic text location of multimedia video for subtitle frame

The traditional multi-media video text auto-positioning is too dependent on man-made function, and its disadvantages are mainly embodied in the aspects of strong subjectivity, large quantity of work, slow processing speed and the like. Through the establishment of the basic framework of multimedia video text search, the feature vectors of multimedia video text are calculated. On the basis of the feature of the independent video captioning (ICA), the method of automatic positioning of the multimedia video text is studied. The method comprises the following steps of: extracting a plurality of ICA image features of an independent multimedia video text sub-block by adopting an independent video caption-based ICA feature extraction method; performing image candidate character line automatic detection based on a plurality of ICA image features, adopting an adaptive iterative positioning algorithm to quickly obtain a character candidate line, In the process of automatic text block detection, the flaw of text candidate line detection is checked, and the text candidate block is obtained by threshold calculation. The experimental results show that the proposed method has the highest accuracy in recognizing video subtitles with independent caption based ICA features, and the recall and precision of the text lines and blocks of the video image are located by the proposed method, and good automatic positioning effect.

Engagement With Crisis Text Line Among Subgroups of Users Who Reported Suicidality.

Despite the interest in technology-enhanced preventive interventions for suicidality, there is minimal peer-reviewed research on conversations of text message hotlines. In this large-scale study, the authors explored distinct classes of users of the Crisis Text Line who reported suicidality. Classes were based on texters' presenting psychosocial issues and were explored across frequency of hotline use and conversation number. Data included 153,514 conversations from 122,909 individuals collected by the Crisis Text Line (2013-2017). Analyses were restricted to conversations from users who mentioned current or previous suicidality and excluded texters who discussed a third party. The authors used latent class analysis to identify distinct classes of texters on the basis of crisis counselor-assigned issue tags and across subgroups reflecting whether the conversation was the first or last contact with the hotline and frequency of use (one-time, two-time, or ≥3-time texters). Three classes emerged in all subsamples. The largest class, "lower distress," had the lowest prevalence of all issues. The second largest class, "anxious distress," had the highest prevalence of anxiety or stress and elevated depression. The smallest class, "relational distress," had the highest prevalence of depression and self-harm and higher probability of endorsing relational indicators. Psychological and relational issues mostly distinguished the three classes. Despite differing frequency of hotline usage, most texters who reported suicidal ideation and behaviors endorsed similar issues, and these issues did not seem to vary across conversations. Yet there appeared to be distinct subgroups of texters with different presenting issues, which may inform how crisis counselors tailor strategies for both low- and high-volume texters.

Word frequency, predictability, and return-sweep saccades: Towards the modeling of eye movements during paragraph reading.

Models of eye movement control during reading focus on the reading of single lines of text. Within these models, word frequency and predictability are important input variables which influence fixation probabilities and durations. However, a comprehensive model of eye movement control will have to account for readers' eye movements across multiline texts. Line-initial words are unlike those presented midline; they are routinely unavailable for parafoveal preprocessing. Therefore, it is unclear whether and how word frequency and predictability influence reading times on line-initial words. To address this, we present an analysis of the Provo Corpus (Luke & Christianson, 2018) followed by a novel eye-movement experiment. We conclude that word frequency and predictability impact single-fixation and gaze durations on line-initial words. We also observed that return-sweep error (undersweep-fixations) may, among several other possibilities, allow for parafoveal processing of line-initial words prior to their direct fixation. Implications for models of eye movement control during reading are discussed. (PsycINFO Database Record (c) 2019 APA, all rights reserved).

A Hybrid Approach for Skew Detection and Correction in the Multi-script Scanned Document

Skew detection and correction of a scanned document is a very important step in Optical Character Recognition because skew of scanned document is reducing the accuracy of text line approach for skew detection and correction to calculate the skew angle on multi-script scanned document using Radon transform, Hough transform, Harries corner, Wiener filter and smearing algorithm. In this paper, a proposed approach is compared existing skew detection and correction techniques for printed documents having different scripts: English, Tamil, Sinhala and mixed-script. A proposed hybrid method is tested on 160 documents. The overall testing results is 90.62% for skew detection and correction.

Delaunay triangulation based text detection from multi-view images of natural scene

Text detection in the wild is still considered as a challenging issue to the researchers because of its several real time applications like forensic application, where CCTV camera captures images at different angles of the same scene. Unlike the existing methods that consider a single view captured orthogonally for text detection, this paper considers multi-view (view-1 and view-2 of the same spot) of the same scene captured at different angles or different height distances for text detection. For each pair of the same scene, the proposed method extracts features that describe characteristics of text components based on Delaunay Triangulation (DT), namely corner points, area and cavity of the DT. The features of corresponding DT in view-1 and view-2 are compared through cosine distance measure to estimate the similarity between two components of respective view-1 and view-2. If the pair satisfies the similarity condition, the components are considered as Candidate Text Components (CTC). In other words, these are the common components for view-1 and view-2 that satisfy the similarity condition. From each CTC of view-1 and view-2, the proposed method finds nearest neighbor components to restore the components of the same text line based on estimating degree of similarly between CTC and neighbor components using Chi-square and cosine distance measures. Furthermore, the proposed method uses a recognition step to detect correct texts by comparing recognition results of view-1 and view-2. The same recognition step is used for removing false positives to improve the performance of the proposed method. Experimental results on our own dataset, which contains pair of images of different situations, and the standard datasets, namely, ICDAR 2013, MSRATD-500, CTW1500, Total-text, ICDAR 2017 MLT and COCO-text, show that the proposed method outperforms the existing methods.

MA-CRNN: a multi-scale attention CRNN for Chinese text line recognition in natural scenes

The recognition methods for Chinese text lines, as an important component of optical character recognition, have been widely applied in many specific tasks. However, there are still some potential challenges: (1) lack of open Chinese text recognition dataset; (2) challenges caused by the characteristics of Chinese characters, e.g., diverse types, complex structure and various sizes; (3) difficulties brought by text images in different scenes, e.g., blur, illumination and distortion. In order to address these challenges, we propose an end-to-end recognition method based on convolutional recurrent neural networks (CRNNs), i.e., multi-scale attention CRNN, which adds three components on the basis of a CRNN: asymmetric convolution, feature reuse network and attention mechanism. The proposed model is mainly aimed at scene text recognition including Chinese characters. Then the model is trained and tested on two Chinese text recognition datasets, i.e., the open dataset MTWI and our constructed large-scale Chinese text line dataset collected from various scenes. The experimental results demonstrate that the proposed method achieves better performance than other methods.

Design of Multi-channel data acquisition system based on single Chip computer and LabVIEW

Labview is a graphical programming language that creates applications with icons instead of text lines. Because the traditional data acquisition system based on single chip computer is not supported by the upper computer, its storage capacity is limited, no matter what kind of data memory is used, so it has to overwrite and refresh the stored historical data. This system uses the lower computer to collect the analog data, and from the single chip computer to collect the eight channels of data, and to answer the command sent by the host. The host computer is responsible for processing and displaying the received digital quantity. The host and slave communicate with each other using RS-232. The paper presents design of Multi-channel data acquisition system based on single Chip computer and LabVIEW.

Unconstrained Handwritten Text Line Segmentation for Kannada Language

Segmentation is division of something into smaller parts and one of the Component of character recognition system. Separation of characters, words and lines are done in Segmentation from text documents. character recognition is a process which allows computers to recognize written or printed characters such as numbers or letters and to change them into a form that the computer can use. the accuracy of OCR system is done by taking the output of an OCR run for an image and comparing it to the original version of the same text. The main aim of this paper is to find out the various text line segmentations are Projection profiles, Weighted Bucket Method. Proposed method is horizontal projection profile and connected component method on Handwritten Kannada language. These methods are used for experimentation and finally comparing their accuracy and results.

New Tools for the Classification and Filtering of Historical Maps

Historical maps constitute an essential information for investigating the ecological and landscape features of a region over time. The integration of heritage maps in GIS models requires their digitalization and classification. This paper presents a semi-automatic procedure for the digitalization of heritage maps and the successive filtering of undesirable features such as text, symbols and boundary lines. The digitalization step is carried out using Object-based Image Analysis (OBIA) in GRASS GIS and R, combining image segmentation and machine-learning classification. The filtering step is performed by two GRASS GIS modules developed during this study and made available as GRASS GIS add-ons. The first module evaluates the size of the filter window needed for the removal of text, symbols and lines; the second module replaces the values of pixels of the category to be removed with values of the surrounding pixels. The procedure has been tested on three maps with different characteristics, the “Historical Cadaster Map for the Province of Trento” (1859), the “Italian Kingdom Forest Map” (1926) and the “Map of the potential limit of the forest in Trentino” (1992), with an average classification accuracy of 97%. These results improve the performance of classification of heritage maps compared to more classical methods, making the proposed procedure that can be applied to heterogeneous sets of maps, a viable approach.

Automated Mobile Phone-Based Mental Health Resource for Homeless Youth: Pilot Study Assessing Feasibility and Acceptability.

BackgroundYouth experiencing housing instability have higher rates of mental health problems than their housed peers. Few studies have evaluated technological resources for homeless youth to determine how to effectively engage and reach them.ObjectiveThe primary aims of this pilot study were to establish the feasibility (as measured by phone retention rates) and acceptability (ie, participant ratings of resources) of delivering automated mental health resources via smartphone technology.MethodsYouth aged 16 to 25 years (N=100) were recruited through homeless shelter agencies in the Chicago metropolitan area. Eligible participants completed a baseline assessment and received a smartphone with a 3-month data plan. The phone was preloaded with several apps designed to promote mental health wellness and provide real-time resources. One app specifically designed for this study, Pocket Helper 2.0, sent participants daily surveys and tips via push notification. The tips focused on coping and motivation, and the surveys assessed mood. This app also included an automated self-help system with brief cognitive behavioral interventions (5-10 min) and access to several interactive mobile tools, including a crisis text line, a telephone hotline, a crowd-based emotional support tool, and an app providing up-to-date information on social service and mental health resources for homeless youth in Chicago. Participants completed assessments at 3 and 6 months.ResultsSome individuals (23%, 23/100) experienced problems with the phones (eg, theft, loss, and technological issues) throughout the study. Participant retention at the midpoint was moderate, with 48% (48/100) of youth responding to the 3-month surveys. At 6 months, only 19% (19/100) of the total sample responded to the end point survey. Overall, 63% (30/48) to 68% (13/19) of respondents at both time points reported benefiting from the intervention; however, participant usage and satisfaction varied with the different features. At both time points, participants reported receiving the most benefit from the daily tips and daily surveys. Daily tips that were most preferred by participants involved motivational tips related to overcoming struggles and making progress in life. Aside from the tips and surveys, the most used features were the app providing up-to-date resources and the automated self-help system. Interactive features, including the telephone hotline and crowd-based emotional support tool, were the least used features and were rated as the least beneficial.ConclusionsAutomated mental health interventions seem to be an acceptable way to engage homeless youth in mental health support. The participants preferred fully automated features and brief interventions over features requiring interaction with others or more engagement. Future research should explore ways to retain homeless youth in interventions and evaluate the clinical impact of automated technology-based interventions for improving mental health.Trial RegistrationClinicalTrials.gov NCT03776422; https://clinicaltrials.gov/ct2/show/NCT03776422

Dissociating lexical and sublexical contributions to transposed-word effects

When two sequences of words are presented successively for 400 ms each, it is harder to decide that the two sequences differ when the difference is generated by transposing two words compared with a condition where the same two words are replaced by different words. Interestingly, this transposed-word effect is obtained even when the first sequence is ungrammatical. One account of the effect seen with ungrammatical sequences is that participants detect mismatching letters rather than words. Under this account, the migration of letter identities across adjacent words would make it harder to judge the transposed-word condition as being different. The present experiment put this account to test by comparing transposition effects to sequences of words vs. pseudowords. We hypothesized that if same-different judgments are made on the basis of sublexical orthographic information only, then we should observe similar effects for words and pseudowords. Although transposition effects were found with pseudoword stimuli, the effects were significantly reduced compared to word sequences. This suggests that the noisy bottom-up allocation of word identities to locations along a line of text is one key mechanism driving transposed-word effects.

MIDV-500: a dataset for identity document analysis and recognition on mobile devices in video stream

A lot of research has been devoted to identity documents analysis and recognition on mobile devices. However, no publicly available datasets designed for this particular problem currently exist. There are a few datasets which are useful for associated subtasks but in order to facilitate a more comprehensive scientific and technical approach to identity document recognition more specialized datasets are required. In this paper we present a Mobile Identity Document Video dataset (MIDV-500) consisting of 500 video clips for 50 different identity document types with ground truth which allows to perform research in a wide scope of document analysis problems. The paper presents characteristics of the dataset and evaluation results for existing methods of face detection, text line recognition, and document fields data extraction. Since an important feature of identity documents is their sensitiveness as they contain personal data, all source document images used in MIDV-500 are either in public domain or distributed under public copyright licenses. The main goal of this paper is to present a dataset. However, in addition and as a baseline, we present evaluation results for existing methods for face detection, text line recognition, and document data extraction, using the presented dataset.

Telugu Character Recognition using Adaptive Fuzzy Membership Functions With Adaptive Genetic Algorithm Based Techniques

A novel Telugu character recognition technique is proposed in this paper where the given Telugu handwritten document is processed by normalizing the document and removing the noise. Then slant detection followed by correction process is conceded using the bilinear interpolation method to get more accurate result. Thus the de-skewed documents text lines and characters are separated by making use of Adaptive Histogram Equalization (AHE). In the next stage, the characteristics of the segmented characters are mined with the help of the zoning method. In zoning method, an adaptive fuzzy membership function will be developed by the Adaptive Genetic Algorithm (AGA). By using AGA in zoning method the characteristics are mined from the separated characters. The mined structures are applied to the Feed Forward Back Propagation Neural Network (FFBNN) for accomplishing the learning process. During testing, more number of handwritten segmented Telugu characters will be set to the FFBNN to verify whether the input character is recognized or not. Thus, the proposed method has given more accurate recognition results by using our proposed adaptive fuzzy membership function with AGA method. The proposed method performance is evaluated by getting more number of handwritten Telugu documents and compared with the GA-FFBNN and FFBNN.

Bill would provide easier access to MH resources for students

In the hope of preventing further deaths due to suicide, a bipartisan group of senators and state representatives, including sponsor Senator John Kennedy (R‐Louisiana) and co‐sponsors Senator Elizabeth Warren (D‐Massachusetts) and Senator John Cornyn (R‐Texas), recently introduced the Improving Mental Health Access for Students Act, Bustle reported Sept. 24. This bill would require public and nonprofit private colleges and universities to put the Crisis Text Line, the National Suicide Prevention Lifeline and the number for a campus mental health center on the back of every student ID. The bill in question has the potential to impact the health of 20 million college students on campuses nationwide. If the bill passes through Congress, which Crisis Text Line hopes to happen this year, colleges and universities would start printing the numbers on new ID cards from then on out. “They wouldn't have to take everybody's IDs and start over,” Ashley Womble, head of communications at Crisis Text Line, said. “There's no cost associated.”

Ogahiy “Zubdatu-t-tavorix” asarining qo‘lyozmalari va adabiy manba sifatidagi qimmati

The article is devoted to the study of the book “Zubdatu-t-tavorih” by a bright representative of classical Uzbek literature Muhammad Rizo Ogahiy. As result of a comparative analysis of five copies of “Zubdatu-t-tavorih” kept at Saint-Petersburg department of Oriental studies institute of Academy of Sciencies of Russia, State library named after S. Shedrin, Oriental studies institute named after Abu Rayhan Beruniy of the Academy of Sciences of Uzbekistan, it was found out that the copy number 821 kept at the treasury of Oriental studies institute named after Abu Rayhan Beruniy of the Academy of Sciences of Uzbekistan is the best among all aforementioned copies of the manuscript.The article covers the history of the creation of “Zubdatu-t-tavorih” . On the basis of comparative analyzing this book with “Tarihi Turkiston” (History of Turkistan) it was proven that “Zubdatu-t-tavorih” is a reliable source on the history of Khiva khanate. The analysis of the samples of verses from the book was used to ground that “Zubdatu-t-tavorih” was a literary source. For example it contains such samples of poetic genres as qasida (odes) (6), masnaviys (70), ghazels (4), rubayis (7), qit’as (10), ta’rix (4), fard (6). Totally the book consists of 1176 verses (2352 lines) of poetic text. Most significant of them were analyzed. Poetic skills of the author of “Zubdatu-t-tavorih” was demonstrated through the analysis of qasidas and ta’rix. The analysis of the samples of the abovementioned genres, their poetics and rhythmic properties were relied on theoretical ideas put forward in “Funun-ul-balogha“ by Shekh Ahmad Tarozi. At the conclusion part of the article, the author was able to prove that this book is a source of rare information on such sciences as history, etnography, toponomy, and others.

Text-line extraction from handwritten document images using GAN

Text-line extraction (TLE) from unconstrained handwritten document images is still considered an open research problem. Literature survey reveals that use of various rule-based methods is commonplace in this regard. But these methods mostly fail when the document images have touching and/or multi-skewed text lines or overlapping words/characters and non-uniform inter-line space. To encounter this problem, in this paper, we have used a deep learning-based method. In doing so, we have, for the first time in the literature, applied Generative Adversarial Networks (GANs) where we have considered TLE as image-to-image translation task. We have used U-Net architecture for the Generator, and Patch GAN architecture for the discriminator with different combinations of loss functions namely GAN loss, L1 loss and L2 loss. Evaluation is done on two datasets: handwritten Chinese text dataset HIT-MW and ICDAR 2013 Handwritten Segmentation Contest dataset. After exhaustive experimentations, it has been observed that U-Net architecture with combination of the said three losses not only produces impressive results but also outperforms some state-of-the-art methods.

Augmented reality cuisine

Augmented reality cuisine

Several steganographic methods using for embedding of hidden data in electronic text documents

The description of the method and algorithm for embedding a hidden message or a digital watermark into files of Microsoft Word electronic documents in .DOCX format based on two steganographic methods is given. A Microsoft Word electronic document in .DOCX format is used as a steganographic container. One of the methods uses the features of displaying a document by a word processor and the word processor allows the displacement of hidden characters, such as spaces, tabs and paragraphs, in the text relatively to the line of text. The second method uses the feature of the .DOCX format electronic text document that a document is an archive containing Open XML format files and media files, so specialized steganographic methods for XML files can be used for embedding a hidden message. In this case the quotes replacement method is used. The embedding of a hidden message by one of the methods is used for checking the integrity of the other message through the second method. Depending on the capacity of the steganographic container a method can be chosen to embed the message anda method to control the integrity of the message. The algorithm of the inverse steganographic transformation for extracting a message and confirming the integrity of an electronic document is considered. The application is developed to perform the embedding of a hidden message in an electronic text document depending on the capacity of the container. The possibility of using of some steganographic methods is analyzed with the aim of forming a multi-key steganographic system intended for a digital watermarking of an electronic document Microsoft Word format .DOCX.