Character Recognition Software Research Articles

Raspberry-Pi Based Physical Media to Audio Conversion device for Visually Impaired Individuals

The proposed product is a device for real-time scanning and conversion of text from physical media to audio for the aid of visually impaired individuals. The focus of the project is to make a device which brings the experience of visually impaired individuals as close to that of the ordinarily abled/educated as possible when it comes to access to resources, books, and physical reading material. This device is targeted towards libraries, reading rooms, and schools for visually impaired individuals. The prototype is developed using a FDM 3D printer with PLA material and using a laser cutting machine with MDF material to allow for maximum customisability to meet the end-user’s needs. The proposed device is equipped with a Raspberry Pi 4B+, a camera, two pushbuttons, two potentiometers and a head-phone. A variety of image processing techniques, bundled with open-source optical character recognition (OCR) software and text-to-speech libraries, are used to capture and process images of book pages and convert them to audio files, all while maintaining a physical user interface which can be navigated autonomously by the visually challenged. The product is capable of handling over 200 fonts from 8pt to 36pt size. The product is successfully tested on 15 users for approximately 4000 words.

Algorithms of the Tiger and CuneiForm Optical Character Recognition Software

Algorithms of the Tiger and CuneiForm Optical Character Recognition Software

Poster (Clinical/Best Practice Implementation) ID 1984972

Background Heart disease is the most common cause of death after spinal cord injury or disease (SCI/D), with Cardiometabolic Disease (CMD) risk a primary contributor. Objectives 1) To report the frequency of Physical Activity guideline adherence; 2) To report the frequency of serum lipid screening recall and their recollection of the result interpretation; among adults living with SCI/D in the community. Methods A Kinesiologist collected the SCI-High outcome data via in person or phone 1:1 interviews, and chart abstraction among UHN outpatients. A Provincial Intake Coordinator collected data via phone interview among outpatients affiliated with SCI Ontario. Survey responses were scored using Reachlite’s optical character recognition software. Descriptive statistics characterize the participant’s age, sex, impairment characteristics, and adherence to physical activity guidelines and the frequency of lipid screening/interpretation recall. Best practice education materials were used to increase future PA guideline adherence, prompt lipid screening, and healthy food choices. Results Adult outpatients (n=127, 67% male), mean age 61 years, and 55% paraplegic consented to participate. In total, 48% (60/126) of outpatients reported engaging in some form of aerobic exercise; of whom 50% (30/60) of these individuals were meeting current PA guidelines. About 51% of outpatients recalled lipid screening within the last year, 33% indicated they had not had an assessment. Clinical interpretation of lipid values was recalled by 71% (53/75) of outpatients. Conclusion Physical activity guideline adherence and routine lipid assessments are integral to CMD risk modification – substantial education resources and recall aids may help to modify CMD risk after SCI/D.

Poster (Clinical/Best Practice Implementation) ID 1984967

Background Assessment of physical activity (PA) prescription recall and serum screening for dyslipidemia are critical to describe and mitigate Cardiometabolic Disease (CMD) risk among adults with spinal cord injury or disease (SCI/D). Objectives To report: 1) the frequency of PA prescription recall; and, 2) the frequency of lipid profile assessment and interpretation recall among inpatients with SCI/D during rehabilitation. Methods Adults with SCI/D completed the SCI-HIGH CMD intermediary outcome indicators. A Kinesiologist collected data via interview and chart abstraction among UHN inpatients. Survey responses were scored using Reachlite’s optical character recognition software. Descriptive statistics were used to characterize the participant’s age, sex, impairment characteristics, and report recall rates and the frequency of lipid screening/interpretation. Based on the participant’s needs, either educational materials to increase future adherence to PA guidelines and/or a Mediterranean diet were provided. Results Adult inpatients (n=124), mean age 59 years, 64% paraplegic, and 36% female participated. In total, 14% of participants (16/117) reported being taught the benefits of PA for their heart health; of whom 69% (11/16) recalled exercise instruction. Similarly, 15% of inpatients (17/114) recalled lipid screening during rehabilitation, although chart abstraction revealed that 30% (37/124) had completed lipid screening. Clinical interpretation of their lipid values was recalled by 30% of inpatients. Conclusion There is a significant opportunity to advance PA instruction and lipid profile education and management among inpatients with SCI/D to reduce CMD risk. Inclusion of PA and lipid management instructions in patient-oriented discharge summaries may enhance patient recall/adherence.

Creating electronic resources for African languages through digitisation: a technical report

The need for electronic resources for (under-resourced) African languages is an often stated one. These resources are needed for language research in general, and more specifically for the development of Human Language Technology (HLT) applications such as machine translation, speech recognition, electronic dictionaries, spelling and grammar checkers, and optical character recognition. These technologies rely on large quantities of high-quality electronic data. Digitisation is one of the strategies that can be used to collect such data. For the purpose of this paper, digitisation is understood as the conversion of analogue text, audio and video data into digital form, as well as the provision of born digital data that is currently not available in a format that enables downstream processing. There is a general perception that the African languages are under-resourced with regard to sufficient digitisation tools to function effectively in the modern digital world. Our paper is presented as a technical report, detailing the tools, procedures, best practices and standards that are utilised by the UP digitisation node to digitise text, audio and audio-visual material for the African languages. The digitisation effort is part of the South African Digital Languages Resources (SADiLaR) project (https://www.sadilar.org/index.php/en/), funded by the Department of Science and Innovation. Our report is based on a best practices document, developed through the course of our digitisation project and forms part of the deliverables as per contractual agreement between the UP digitisation node and the SADiLaR Hub. The workflow as explained in this document was designed with this specific project in mind; software and hardware utilised were also selected based on the constraints with regard to capacity and available technical skills in mind. We motivate our choice of Optical Character Recognition (OCR) software by referring to an earlier experiment in which we evaluated three commercially available OCR programmes. We did not attempt a full-scale evaluation of all available OCR software, but rather focused on selecting one that renders high quality outputs. We also reflect on one of the challenges specific to our project, i.e. copyright clearance. This is particularly relevant with regard to published material. In the absence of newspapers for specifically the African Languages (isiZulu being a notable exception), the biggest portion of textual material available for digitisation consists of printed material such as textbooks, novels, dramas, short stories and other literary genres. The digitisation process is driven by the availability of material for the different languages. Furthermore, obtaining copyright clearance from publishers is a prerequisite for digitisation and especially for the release of any digitised text data for further use and/or processing. Having information on a relatively small-scale digitisation workflow and best practices readily available will enable other interested parties to participate in the digitisation effort, thus contributing to the collection of electronic data for the African languages.

A Proposal of Printed Table Digitization Algorithm with Image Processing

Nowadays, digital transformation (DX) is the key concept to change and improve the operations in governments, companies, and schools. Therefore, any data should be digitized for processing by computers. Unfortunately, a lot of data and information are printed and handled on paper, although they may originally come from digital sources. Data on paper can be digitized using an optical character recognition (OCR) software. However, if the paper contains a table, it becomes difficult because of the separated characters by rows and columns there. It is necessary to solve the research question of “how to convert a printed table on paper into an Excel table while keeping the relationships between the cells?” In this paper, we propose a printed table digitization algorithm using image processing techniques and OCR software for it. First, the target paper is scanned into an image file. Second, each table is divided into a collection of cells where the topology information is obtained. Third, the characters in each cell are digitized by OCR software. Finally, the digitalized data are arranged in an Excel file using the topology information. We implement the algorithm on Python using OpenCV for the image processing library and Tesseract for the OCR software. For evaluations, we applied the proposal to 19 scanned and 17 screenshotted table images. The results show that for any image, the Excel file is generated with the correct structure, and some characters are misrecognized by OCR software. The improvement will be in future works.

Optical Character Recognition For Invent And Outcome Management At The Batang Toru Camat Office, Tapanuli Selatan

The system for managing incoming and outgoing mail at the Batang TORU Camat Office, Selatan Tapanuli includes incoming letters, outgoing letters, archives, and so on. Archives are a source of information from various fields that will be stored in storage areas. The purpose of writing this final project report is to find out how to handle incoming and outgoing mail manually and computerized at the Batang Toru Camat Office, Selatan Tapanuli filling by using the application and knowing the handlers of hadrcopy documents into softcopy online using optical character recognition (OCR). This Final Project report writing method is carried out by means of literature studies, observations and interviews with resource persons at the Batang Toru Camat Office, Selatan Tapanuli. From the results of observations and interviews, it is known that the handling of incoming and outgoing letters is carried out using a manual and computerized system. Incoming mail flow system starts from the recipient then is followed up to each unit and then archived. Outgoing mail is processed from drafting letters to sending outgoing letters. Electronic filing management (e-filing) using the application. Application of hardcopy documents that will be converted into softcopy using Optical Character Recognition (OCR) software, without having to type as the original. The software can be done online for free without registering first.

Facilitating clinical research through automation: Combining optical character recognition with natural language processing.

Performance status is crucial for most clinical research, as an eligibility criterion, a comorbidity covariate, or a trial endpoint. Yet information on performance status often is embedded as free text within a patient's electronic medical record, rather than coded directly, thereby making this concept extremely difficult to extract for research. Furthermore, performance status information frequently resides in outside reports, which are scanned into the electronic medical record along with thousands of clinic notes. The image format of scanned documents also is a major obstacle to the search and retrieval of information, as natural language processing cannot be applied to unstructured text within an image. We, therefore, utilized optical character recognition software to convert images to a searchable format, allowing the application of natural language processing to identify pertinent performance status data elements within scanned electronic medical records. Our study cohort consisted of 189 subjects diagnosed with diffuse large B-cell lymphoma for whom performance status was a required data element for analysis of prognostic factors related to recurrence and survival. Manual abstraction of performance status was previously conducted by a clinical Subject Matter Expert, serving as the gold standard. Leveraging our data warehouse, we extracted relevant scanned electronic medical record documents and applied optical character recognition to these images using the ABBYY FineReader software. The Linguamatics i2e natural language processing software was then used to run queries for performance status against the corpus of electronic medical record documents. We evaluated our optical character recognition/natural language processing pipeline for accuracy and reduction in data extraction effort. We found that there was high accuracy and reduced time for extraction of performance status data by applying our optical character recognition/natural language processing pipeline. The transformed scanned documents from a random sample of patients yielded excellent precision, recall, and F score, with <1% incorrect results. Time savings from a second cohort showed that median time to review documents for patients with performance status data present was reduced by a third. The major time savings was in the review of those documents that in fact did not contain performance status information: median of 18 minutes versus 108 minutes for manual review, an 83% reduction in data abstraction effort. By applying this optical character recognition/natural language processing pipeline, we achieved significant operational improvement and reduced time for information retrieval to support clinical research. Our study demonstrated that optical character recognition software provides an effective mechanism to transform scanned electronic medical record images to allow the application of natural language processing, yielding highly accurate data abstraction. We conclude that our optical character recognition/natural language processing pipeline can greatly facilitate research data abstraction by providing a highly focused data review, eliminating unnecessary manual review of the entire chart, and thus freeing time for abstracting other data elements requiring more human interpretation.

Dielectric Elastomer Actuators and Optical Character Recognition in a Braille Display

The purpose of this study was the development and experimental validation of a novel portable tactile braille reading device. This design aimed to address the lack of quality braille reading material in South African schools dedicated to the blind and visually impaired. The design was divided into four subsystems: the actuation of the refreshable braille display, the mechanical design of the hand mounted device, the Optical Character Recognition (OCR) software and the electronic control system. The objectives of the study included the design of the electrical, mechanical and software subsystems of the device with emphasis on miniaturisation and a low-cost design, as well as the experimental validation of the haptic feedback and OCR subsystems. The system validation focussed on the experimental analysis of the OCR software design and the Dielectric Elastomer Actuators (DEAs) utilised in the refreshable display. The performance of low-cost elastomer and electrode materials were experimentally assessed during the design of the miniature DEAs. The ideal material combination for the proposed application was identified as a VHB4910 acrylic film lined with MG Chemicals 846 carbon grease. The largest vertical deflections of the diaphragm-type DEA were attained with a stipple-based electrode application, with the elastomer prestrained to 300 % initial area. The OCR program analysis indicated that multiple character recognition was more efficient and less prone to inaccuracies than the initially proposed single character recognition method. The integration of OCR software with miniature DEAs served as a novel approach to text-to-braille transcription.

Design of an automatic license plate reader

The increase in the number of vehicles and the alarming rate of theft and defaulters daily prompts the need for sophisticated matching technology to curb car theft, reduce traffic offenders, and any other anomalies/irregularities affecting vehicles’ smooth operation. This study deals with the design of an automatic license plate reader which automatically captures an image of the vehicle’s license plate, transforms that image into alphanumeric characters using optical character recognition or similar high-tech software, and compares the plate number acquired to one or more databases of vehicles of interest to law enforcement and other agencies against those of stolen cars or people suspected of being involved in criminal activities. The automated capture, analysis, and comparison of vehicle license plates typically occur within seconds enabling the officer in charge to take appropriate actions.

EVALUATION OF THE MOBILE LEARNING APPLICATIONS THAT CAN BE USED TO DEVELOP ENGLISH LANGUAGE SKILLS AMONG STUDENTS WITH BLINDNESS IN THE INCLUSIVE CLASS

This study aimed to evaluate the mobile applications that can be used in the inclusive classroom to teach and enhance English language skills among students with blindness. The analytical research design was employed in the current study. Using specific keywords and criteria, a total of 64 Voice Recognition Software (VRS), 31 Optical Character Recognition software (OCR), 34 Text to Speech software (TTS), and 59 e-Dictionaries available in android platform from January to August 2021 were analyzed using accessibility and usability checklist prepared by the authors. The tool's validity and consistency were gained through experts' good judgment and following the inter-rater reliability method. The findings of the study revealed that Google Assistant, Google Translator, SayHi Translator, and Talking Translator were ranked first among the VRS and e-Dictionaries, so they are considered as the best VRS and e-Dictionaries available in android platform that can be used to develop vocabulary and speaking skills among students with blindness. Whereas, Scanner Go, Clear Scanner, vFlat, Documents Scanner, Google Lens and Fast Scan Apps were ranked first among the OCR software. However, T2S, @Voice, Google Lens, and TTS Reader Apps were ranked first among the TTS Apps and considered as the best free TTS Apps available in android platform. Therefore, they are highly recommended to be used by general teachers in inclusive settings to compensate the lack of special technology, adapt the English subject curriculum for students with blindness, and enhance the students' self-learning and participation in the English class.

PNRank: Unsupervised ranking of person name entities from noisy OCR text

Text databases have grown tremendously in number, size, and volume over the last few decades. Optical Character Recognition (OCR) software is used to scan the text and make them available in online repositories. The OCR transcription process is often not accurate resulting in large volumes of garbled text in the repositories. Spell correction and other post-processing of OCR text often prove to be very expensive and time-consuming. While it is possible to rely on the OCR model to assess the quality of text in a corpus, many natural language processing and information retrieval tasks prefer the extrinsic evaluation of the effect of noise on the task at hand. This paper examines the effect of noise on the unsupervised ranking of person name entities by first populating a list of person names using an out-of-the-box Named Entity Recognition (NER) software, extracting content-based features for the identified entities, and ranking them using a novel unsupervised Kernel Density Estimation (KDE) based ranking algorithm. This generative model has the ability to learn rankings using the data distribution and therefore requires limited manual intervention. Empirical results are presented on a carefully curated parallel corpus of OCR and clean text and “in the wild” using a large real-world corpus. Experiments on the parallel corpus reveals that even with a reasonable degree of noise in the dataset, it is possible to generate ranked lists using the KDE algorithm with a high degree of precision and recall. Furthermore, since the KDE algorithm has comparable performance to state-of-the-art unsupervised rankers, using it on real-world corpora is feasible. The paper concludes by reflecting on other methods for enhancing the performance of the unsupervised algorithm on OCR text such as cleaning entity names, disambiguating names concatenated to one another and correcting OCR errors that are statistically significant in the corpus.

The Smart Assistant for Library Management and Book Reader for Blind People Using Raspberry Pi

This system proposes a camera-based assistive text reading framework to help blind persons ad text labels and product packaging from hand-held objects in their daily lives. To isolate the object from cluttered backgrounds or other surrounding objects in the camera view, we rest propose an ancient and active motion-based method to dine a Region Of Interest (ROI) in the video by asking the user to shake the object. In the extracted ROI, text localization and recognition are conducted to acquire text information. To automatically localize the text regions from the object ROI, we propose a novel text localization algorithm by learning gradient features of stroke orientations and distributions of edge pixels in an Ad boost model. Text characters in the localized text regions are then binaries and recognized by the shelf Optical Character Recognition (OCR) software.

Automatic calibration with character recognition software

This work presents the development and implementation of a character recognition software of digital displays with serial communication for the automation of the readings, registry and transcription of measurement instrument’s indications during calibrations. The software proved to be flexible, allowing calibrations with automatic registry, reducing transcription errors, improving the work conditions and organizing the registers, besides allow remote calibrations.

WITHDRAWN: Robokart for visually impaired people

Abstract This paper proposes a system that can be installed on a shopping cart that be used to assist visually impaired people. This method uses the concept of ROI, text localization and recognition by optical character recognition software and a webcam controlled by Raspberry Pi. Two micro controllers are used to program both the shopping cart movement and OCR. The user is required to give a voice input of the required product and the ROBOKART guides the user to that product.

Vision-based patient identification recognition based on image content analysis and support vector machine for medical information system

In this paper, a vision-based patient identification recognition system based on image content analysis and support vector machine is proposed for medical information system, especially in dermatology. This proposed system is composed of three parts: pre-processing, candidate region detection, and digit recognition. To consider the efficiency of the proposed scheme, image normalization is performed. The color information is used to identify camera-captured screen images. In the pre-processing part, the effect of noise in captured screen images is reduced by a bilateral filter. The color and spatial information is used to initially and roughly locate the candidate region. To reduce the skew effect, a skew correction algorithm based on the Hough transform is developed. A template matching algorithm is used to find special symbols for locating the region of interest (ROI). For digit segmentation, digits are segmented in the ROI based on the vertical projection and adaptive thresholding. For the digit recognition, some features are measured from each digit segment and a classifier based on the support vector machine is applied to recognize digits.The experiment’s results show that the proposed system could effectively not only use color information to distinguish the captured screen images from the skin images but also detect the ROIs. After the digit segmentation, the accuracy rates of digit recognition are 98.4% and 94.2% for the proposed system and the Tesseract Optical Character Recognition (OCR) software, respectively. These results demonstrate that the proposed system outperforms the Tesseract OCR software in terms of the accuracy rate of digit recognition.

Stroke Extraction for Offline Handwritten Mathematical Expression Recognition

Offline handwritten mathematical expression recognition is often considered much harder than its online counterpart due to the absence of temporal information. In order to take advantage of the more mature methods for online recognition and save resources, an oversegmentation approach is proposed to recover strokes from textual bitmap images automatically. The proposed algorithm first breaks down the skeleton of a binarized image into junctions and segments, then segments are merged to form strokes, finally stroke order is normalized by using recursive projection and topological sort. Good offline accuracy was obtained in combination with ordinary online recognizers, which are not specially designed for extracted strokes. Given a ready-made state-of-the-art online handwritten mathematical expression recognizer, the proposed procedure correctly recognized 58.22%, 65.65%, and 65.22% of the offline formulas rendered from the datasets of the Competitions on Recognition of Online Handwritten Mathematical Expressions(CROHME) in 2014, 2016, and 2019 respectively. Furthermore, given a trainable online recognition system, retraining it with extracted strokes resulted in an offline recognizer with the same level of accuracy. On the other hand, the speed of the entire pipeline was fast enough to facilitate on-device recognition on mobile phones with limited resources. To conclude, stroke extraction provides an attractive way to build optical character recognition software.

A Smart Reader for Blind People A Smart Reader for Blind People A Smart Reader for Blind People A Smart Reader for Blind People A Smart Reader for Blind People A Smart Reader for Blind People A Smart Reader for Blind People A Smart Reader for Blind People A Smart Reader for Blind People A

This paper presents an intelligent bot for aiding the visually challenged people. Presently, 81% are visually impaired who live in the developing countries. Nowadays Human communication is mainly focused on text and speech. To read the text a human needs a vision. Survey conducted on several papers and systems provides hardware consisting of a camera interface with Raspberry Pi for processing the text. The camera captures text image of a handwritten or printed text. The raspberry pi makes use of Optical Character Recognition (OCR) software installed in it, to perform the conversion of an image to text and similarly text to speech conversion. The assistant is applicable for visually impaired people as well as for normal people in order to increase their level of comfort.

LightningBug ONE: An experiment in high-throughput digitization of pinned insects

Digital technology presents us with new and compelling opportunities for discovery when focused on the world's natural history collections. The outstanding barrier to applying existing and forthcoming computational methods for large-scale study of this important resource is that it is (largely) not yet in the digital realm. Without development of new and much faster methods for digitizing objects in these collections, it will be a long time before these data are available in digital form. For example, methods that are currently employed for capturing, cataloguing, and indexing pinned insect specimen data will require many tens of years or more to process collections with millions of dry specimens, and so we need to develop a much faster pipeline. In this paper we describe a capture system capable of collecting and archiving the imagery necessary to digitize a collection of circa 4.5 million specimens in one or two years of production operation. To minimize the time required to digitize each specimen, we have proposed (Hereld et al. 2017) developing multi-camera systems to capture the pinned insect and its accompanying labels from many angles in a single exposure. Using a sampling (21 randomly drawn drawers, totalling 5178 insects) of the 4.5 million specimens in the collection at the Field Museum of Natural History, we estimated that a large fraction of that collection (97.6% +/- 2.2%) consists of pinned insects with labels that are visible from one angle or another without requiring adjustment or removal of elements on the pin. In this situation a multi-camera system with enough angular coverage could provide imagery for reconstructing virtual labels from fragmentary views taken from different directions. Agarwal et al. (2018) demonstrated a method for combining these multiple views into a virtual label that could be transcribed by automated optical character recognition software. We have now designed, built and tested a prototype snapshot 3D digitization station to allow rapid capture of multi-view imagery for automated capture of pinned insect specimens and labels. It consists of twelve very small and light 8-megapixel cameras (Fig. 1), each controlled by a small dedicated computer. The cameras are arrayed around the target volume, six on each side of the sample feed path. Their positions and orientations are fixed by a 3D-printed scaffolding designed for the purpose. The twelve camera controllers and a master computer are connected to a dedicated high-speed data network over which all of the coordinating control signals and returning images and metadata are passed. The system is integrated with a high-performance object store that includes a database for metadata and the archived images comprising each snapshot. The system is designed so that it can be readily extended to include additional or different sensors. The station is meant to be fed with specimens by a conveyor belt whose motion is coordinated with the exposure of the multi-view snapshots. In order to test the performance of the system we added a recirculating specimen feeder designed expressly for this experiment. With it integrated into the system in place of a conventional conveyor belt we are able to provide a continuous stream of targets for the digitization system to facilitate long tests of its performance and robustness. We demonstrated the ability to capture data at a peak rate of 1400 specimens per hour and an average rate of 1000 specimens per hour over the course of a sustained 6 hour run. The dataset (Hereld and Ferrier 2018) collected in this experiment provides fodder for the further development of algorithms for the offline reconstruction and automatic transcription of the label contents.

Introduction to the Symposium: Improving access to hidden scientific data in the Biodiversity Heritage Library

This will be a short introduction to the symposium: Improving access to hidden scientific data in the Biodiversity Heritage Library. The symposium will present examples of how the Biodiversity Heritage Library (BHL) collaborates across the international consortium and with community partners around the world to help enhance access to the biodiversity literature. Literature repositories, particularly the BHL collections, have been recognized as critical to the global scientific community. A diverse global user community propels BHL and BHL users to develop access tools beyond the standard “title, author, subject” search. BHL utilizes the Global Names Recognition and Discovery (GNRD) service to identify taxonomic names within text rendered by Optical Character Recognition (OCR) software, enabling scientific name searches and creation of species-specific bibliographies, critical to systematics research. In this symposium, we will hear from international partners and creative users making data from the BHL globally accessible for the kinds of larger-scale analysis enabled by BHL’s full-text search capabilities and Application Program Interface (API) protocols. In addition to taxonomic name services already incorporated in BHL, the consortium has also begun exploring georeferencing strategies for better searching and potential connections with key biodiversity resources such as the Global Biodiversity Information Facility (GBIF). With many different institutions around the world participating, the ability to work together virtually is critical for a seamless end product that meets the demands of the international community as well as the needs of local institutions.