Optical Character Recognition Accuracy Research Articles

Deep learning-based digitization of Kurdish text handwritten in the e-government system

Many government institutions in developing countries such as the Kurdistan Region of Iraq (KRI) keep a variety of paper-based records that are available in printed or handwritten format. The need for technology that turns handwritten writing into digital text is therefore highly demanded. E-government in developed and developing countries is a crucial facilitator for the provision of such services. This paper aims to develop a deep learning model based on the mask region convolutional neural network (mask-RCNN) to effectively digitize kurdish handwritten text recognition (KHTR). In this research, typical datasets, which includes the isolated handwritten Central Kurdish character images, an extensive database of 40,410 images, and 390 native writers have been produced to determine the developed approach’s performance in terms of identification rates. This approach achieves adequate outcomes in terms of training time and accuracy. The proposed model gives higher performance for detection, localization, and recognition when using a dataset containing many challenges, the results were 80%, 96%, and 87.6 for precision, recall, and F-score respectively. The findings revealed that the proposed model obtained better results compared to other similar works. The accuracy of optical character recognition (OCR) is more than 99%.

Implementing AI on low-power embedded devices for digital water meter identification and data transfer via lora network

This study introduces an artificial intelligence system implemented on the ESP32-CAM platform, aimed at conducting optical character recognition (OCR) on water meters. Leveraging LoRa technology for data transmission ensures efficient energy utilization and convenient long-range communication capabilities. The system achieves an impressive accuracy rate of 98.2% in identifying water meter readings, showcasing its reliability. Proposed as a feasible solution, it offers the advantages of low energy consumption, cost-effectiveness, and flexibility in widespread deployment, particularly leveraging existing water meter infrastructure. Thus, this research presents a promising choice for various applications beyond merely reading water meter readings. Its efficient and accurate OCR functionality makes it suitable for diverse scenarios, ranging from smart city initiatives to industrial automation processes. With its ability to integrate seamlessly into existing infrastructure and deliver reliable results, this system stands poised to revolutionize OCR applications in various domains, contributing to enhanced efficiency and productivity.

Optimizing OCR Performance for Programming Videos: The Role of Image Super-Resolution and Large Language Models

The rapid evolution of video programming tutorials as a key educational resource has highlighted the need for effective code extraction methods. These tutorials, varying widely in video quality, present a challenge for accurately transcribing the embedded source code, crucial for learning and software development. This study investigates the impact of video quality on the performance of optical character recognition (OCR) engines and the potential of large language models (LLMs) to enhance code extraction accuracy. Our comprehensive empirical analysis utilizes a rich dataset of programming screencasts, involving manual transcription of source code and the application of both traditional OCR engines, like Tesseract and Google Vision, and advanced LLMs, including GPT-4V and Gemini. We investigate the efficacy of image super-resolution (SR) techniques, namely, enhanced deep super-resolution (EDSR) and multi-scale deep super-resolution (MDSR), in improving the quality of low-resolution video frames. The findings reveal significant improvements in OCR accuracy with the use of SR, particularly at lower resolutions such as 360p. LLMs demonstrate superior performance across all video qualities, indicating their robustness and advanced capabilities in diverse scenarios. This research contributes to the field of software engineering by offering a benchmark for code extraction from video tutorials and demonstrating the substantial impact of SR techniques and LLMs in enhancing the readability and reusability of code from these educational resources.

Enhancing optical character recognition: Efficient techniques for document layout analysis and text line detection

AbstractIn recent years, automatic document and text analysis has gained significant importance, driven by advancements in optical character recognition (OCR) technology and the need for efficient processing of large volumes of printed or handwritten documents. This article specifically focuses on document layout analysis (DLA) and text line detection (TLD), both of which are crucial components of OCR systems. Our objective is to develop an effective method for extracting both textual and non‐textual regions, addressing challenges unique to the Persian (and Persian‐like) language(s). In the DLA stage, we employ deep learning models and a voting system to accurately determine the regions of interest. Additionally, we introduce methods such as optimum font size concepts, angle correction, and a line curvature elimination algorithm in the TLD process to enhance OCR accuracy. Comparative evaluations against state‐of‐the‐art methods demonstrate the superiority of our approach, showcasing a 2.8% improvement in the accuracy of Tesseract‐OCR 5.1.0 (a well‐established commercial OCR system) on the official Iranian newspapers dataset. These findings underscore the importance of addressing DLA and TLD challenges to advance OCR technology for Persian language documents and provide a solid foundation for future research in this domain.

Advancing OCR Accuracy in Image-to-LaTeX Conversion—A Critical and Creative Exploration

This paper comprehensively assesses the application of active learning strategies to enhance natural language processing-based optical character recognition (OCR) models for image-to-LaTeX conversion. It addresses the existing limitations of OCR models and proposes innovative practices to strengthen their accuracy. Key components of this study include the augmentation of training data with LaTeX syntax constraints, the integration of active learning strategies, and the employment of active learning feedback loops. This paper first examines the current weaknesses of OCR models with a particular focus on symbol recognition, complex equation handling, and noise moderation. These limitations serve as a framework against which the subsequent research methodologies are assessed. Augmenting the training data with LaTeX syntax constraints is a crucial strategy for improving model precision. Incorporating symbol relationships, wherein contextual information is considered during recognition, further enriches the error correction. This paper critically examines the application of active learning strategies. The active learning feedback loop leads to progressive improvements in accuracy. This article underlines the importance of uncertainty and diversity sampling in sample selection, ensuring that the dynamic learning process remains efficient and effective. Appropriate evaluation metrics and ensemble techniques are used to improve the operational learning effectiveness of the OCR model. These techniques allow the model to adapt and perform more effectively in diverse application domains, further extending its utility.

Deep Learning-Based Multifunctional End-to-End Model for Optical Character Classification and Denoising

Optical Character Recognition (OCR) has revolutionized document processing by converting scanned documents, PDFs, and images captured by cameras into editable and searchable text. This technology is crucial for digitizing historical documents, streamlining data entry processes, and improving accessibility for the visually impaired through text-to-speech technologies. Despite its widespread application, OCR faces significant challenges, especially in accurately recognizing text in noisy or degraded images. Traditionally, OCR systems have treated noise reduction and character classification as separate stages, which can compromise the overall effectiveness of text recognition. Our research introduces a groundbreaking Multifunctional End-to-End Model for Optical Character Classification and Denoising, which integrates these functions within a unified framework. By employing a dual-output autoencoder, our model concurrently denoises images and recognizes characters, thereby enhancing both the efficiency and accuracy of OCR. This paper outlines the model's development and implementation, explores the interplay between denoising and classification, and presents compelling experimental results that demonstrate marked improvements over conventional OCR methods.

Gradual OCR: An Effective OCR Approach Based on Gradual Detection of Texts

In this paper, we present a novel approach to optical character recognition that incorporates various supplementary techniques, including the gradual detection of texts and gradual filtering of inaccurately recognized texts. To minimize false negatives, we attempt to detect all text by incrementally lowering the relevant thresholds. To mitigate false positives, we implement a novel filtering method that dynamically adjusts based on the confidence levels of recognized texts and their corresponding detection thresholds. Additionally, we use straightforward yet effective strategies to enhance the optical character recognition accuracy and speed, such as upscaling, link refinement, perspective transformation, the merging of cropped images, and simple autoregression. Given our focus on Korean chart data, we compile a mix of real-world and artificial Korean chart datasets for experimentation. Our experimental results show that our approach outperforms Tesseract by approximately 7 to 15 times and EasyOCR by 3 to 5 times in accuracy, as measured using a Jaccard similarity-based error rate on our datasets.

Pixel-Level Degradation for Text Image Super-Resolution and Recognition

In the realm of image reconstruction, deep learning-based super-resolution (SR) has established itself as a prevalent technique, particularly in the domain of text image restoration. This study aims to address notable deficiencies in existing research, including constraints imposed by restricted datasets and challenges related to model generalization. Specifically, the goal is to enhance the super-resolution network’s reconstruction of scene text image super-resolution and utilize the generated degenerate dataset to alleviate issues associated with poor generalization due to the sparse scene text image super-resolution dataset. The methodology employed begins with the degradation of images from the MJSynth dataset, using a stochastic degradation process to create eight distinct degraded versions. Subsequently, a blank image is constructed, preserving identical dimensions to the low-resolution image, with each pixel sourced randomly from the corresponding points across the eight degraded images. Following several iterations of training via Finetune, the LR-HR method is applied to the TextZoom dataset. The pivotal metric for assessment is optical character recognition (OCR) accuracy, recognized for its fundamental role in gauging the pragmatic effectiveness of this approach. The experimental findings reveal a notable enhancement in OCR accuracy when compared to the TBSRN model, yielding improvements of 2.4%, 2.3%, and 4.8% on the TextZoom dataset. This innovative approach, founded on pixel-level degradation, not only exhibits commendable generalization capabilities but also demonstrates resilience in confronting the intricate challenges inherent to text image super-resolution.

Gpu-based and streaming-enabled implementation of pre-processing flow towards enhancing optical character recognition accuracy and efficiency

Gpu-based and streaming-enabled implementation of pre-processing flow towards enhancing optical character recognition accuracy and efficiency

Digital Forensic Analysis of Vehicular Video Sensors: Dashcams as a Case.

Dashcams are considered video sensors, and the number of dashcams installed in vehicles is increasing. Native dashcam video players can be used to view evidence during investigations, but these players are not accepted in court and cannot be used to extract metadata. Digital forensic tools, such as FTK, Autopsy and Encase, are specifically designed for functions and scripts and do not perform well in extracting metadata. Therefore, this paper proposes a dashcam forensics framework for extracting evidential text including time, date, speed, GPS coordinates and speed units using accurate optical character recognition methods. The framework also transcribes evidential speech related to lane departure and collision warning for enabling automatic analysis. The proposed framework associates the spatial and temporal evidential data with a map, enabling investigators to review the evidence along the vehicle's trip. The framework was evaluated using real-life videos, and different optical character recognition (OCR) methods and speech-to-text conversion methods were tested. This paper identifies that Tesseract is the most accurate OCR method that can be used to extract text from dashcam videos. Also, the Google speech-to-text API is the most accurate, while Mozilla's DeepSpeech is more acceptable because it works offline. The framework was compared with other digital forensic tools, such as Belkasoft, and the framework was found to be more effective as it allows automatic analysis of dashcam evidence and generates digital forensic reports associated with a map displaying the evidence along the trip.

Unveiling the potential of pre-processing and differentiable binarization thresholds for invoice text detection

Invoice text detection aims to automatically identify key information in invoices, which is one of the representative applications of Optical Character Recognition (OCR) technology and a research hotspot in the computer vision community. The classic traditional OCR method consists of three key steps: preprocessing stage, text detection and text recognition. In the feature extraction stage, it faces problems such as insufficient generalization ability and poor robustness. In this paper, we reveal the great potential of preprocessing strategies in improving OCR accuracy, and propose an invoice text detection method based on DBNet and differentiable binarization thresholds. Specifically, we first introduce color segmentation and local adaptive threshold to improve the preprocessing process, which can effectively suppress the influence of background information and context noise on detection results. In addition, a differentiable binarization threshold is introduced in the feature extraction, which improves the error correction speed in the whole deep learning process. Studies have shown significant improvements in test results after color segmentation or background removal compared to the original image. Therefore, we propose to properly consider the text detection of invoices in the preprocessing stage for improvement.

Artificially Intelligent Readers: An Adaptive Framework for Original Handwritten Numerical Digits Recognition with OCR Methods

Advanced artificial intelligence (AI) techniques have led to significant developments in optical character recognition (OCR) technologies. OCR applications, using AI techniques for transforming images of typed text, handwritten text, or other forms of text into machine-encoded text, provide a fair degree of accuracy for general text. However, even after decades of intensive research, creating OCR with human-like abilities has remained evasive. One of the challenges has been that OCR models trained on general text do not perform well on localized or personalized handwritten text due to differences in the writing style of alphabets and digits. This study aims to discuss the steps needed to create an adaptive framework for OCR models, with the intent of exploring a reasonable method to customize an OCR solution for a unique dataset of English language numerical digits were developed for this study. We develop a digit recognizer by training our model on the MNIST dataset with a convolutional neural network and contrast it with multiple models trained on combinations of the MNIST and custom digits. Using our methods, we observed results comparable with the baseline and provided recommendations for improving OCR accuracy for localized or personalized handwritten text. This study also provides an alternative perspective to generating data using conventional methods, which can serve as a gold standard for custom data augmentation to help address the challenges of scarce data and data imbalance.

An approach for improving Optical Character Recognition using Contrast enhancement technique

Digital cameras and mobile image capture of documents are two examples of new developments in the fields of optical character recognition and text recognition. Scans of text or text photographic images and even natural photography results can be distorted to the point where OCR digitization is inaccurate. It offers a unique non-parametric unattended approach to correct unwanted document image distortions to achieve optimal OCR accuracy. It applies a highly effective stack of document image enhancement algorithms to restore perfect images distorted by unknown sources of distortion. First, it provides a means of modifying local brightness and contrast in order to better handle different illumination levels and atypical light transmission patterns in the image. Then apply a nifty grayscale conversion method to your photo to give it a new look. Third, it uses unsharp masking techniques to further enhance important details in grayscale images. Finally, we use the best global binarization technique to prepare the final document image for OCR recognition. The proposed technique has the potential to significantly improve the text recognition rate and accuracy of optical character recognition.

Deep Learning Process and Application for the Detection of Dangerous Goods Passing through Motorway Tunnels

Automated deep learning and data mining algorithms can provide accurate detection, frequency patterns, and predictions of dangerous goods passing through motorways and tunnels. This paper presents a post-processing image detection application and a three-stage deep learning detection algorithm that identifies and records dangerous goods’ passage through motorways and tunnels. This tool receives low-resolution input from toll camera images and offers timely information on vehicles carrying dangerous goods. According to the authors’ experimentation, the mean accuracy achieved by stage 2 of the proposed algorithm in identifying the ADR plates is close to 96% and 92% of both stages 1 and 2 of the algorithm. In addition, for the successful optical character recognition of the ADR numbers, the algorithm’s stage 3 mean accuracy is between 90 and 97%, and overall successful detection and Optical Character Recognition accuracy are close to 94%. Regarding execution time, the proposed algorithm can achieve real-time detection capabilities by processing one image in less than 2.69 s.

Car-Plate Image Enhancement by Using Median and Max Filters


 
 
 
 Nowadays, Optical Character recognition is one of the affected tools for recognition the plate of car from a still video or image in the intelligent transportation systems. The Optical Character Recognition accuracy incompletely depends on the input image quality. In this article, two efficient approaches are proposed to enhance the quality of the car plate image selected from video clips. To minimize the error rate the proposed technique is used even at low resolution image. Maximum, and median filters are used in this work to enhance the quality of image. These technique extend to collect the pixels of the consecutive frames of the video in filtering approaches. The error rate of the OCR is tested on fifty road and street video clips by decreasing the resolution of the images and filtering them with common and proposed filtering methods. The test results indicate that both proposed methods, improve the accuracy of OCR, and the highest reduction of error is obtained by the proposed temporal maximum filtering method.
 
 
 
 

Chimp Optimization Algorithm to Optimize a Convolutional Neural Network for Recognizing Persian/Arabic Handwritten Words

Handwritten character recognition is an attractive subject in computer vision. In recent years, numerous researchers have implemented techniques to recognize handwritten characters using optical character recognition (OCR) approaches for many languages. One the most common methods to improve the OCR accuracy is based on convolutional neural networks (CNNs). A CNN model contains several kernels accompanying with pooling layers and nonlinear functions. This model overcomes the problem of adjusting the value of weights and interconnections of the neural network (NN) for creating an appropriate pipeline to process the spatial and temporal information. However, the training process of a CNN is a challenging issue. Various optimization strategies have been recently utilized for optimizing CNN’s biases and weights such as firefly algorithm (FA) and ant colony optimization (ACO) algorithms. In this study, we apply a well-known nature-inspired technique called chimp optimization algorithm (ChOA) to train a classical CNN structure LeNet-5 for Persian/Arabic handwritten recognition. The proposed method is tested on two known and publicly available handwritten word datasets. To deeply investigate and evaluate the approach, the results are compared with three optimization methods including ACO, FA, and particle swarm optimization (PSO). Outcomes indicated that the proposed ChOA technique considerably improves the performance of the original LeNet model and also shows a better performance than the others.

Reading in the mist: high-quality optical character recognition based on freely available early modern digitized books

Abstract In this paper, we present a workflow for reworking digitized versions of early modern books, freely available in the public domain, in such a way that they will be capable of yielding high-quality optical character recognition (OCR) results suitable for computational text mining. Testing our method, we observed that anything above 90% OCR accuracy is sufficient for semantic analysis. In addition,the overall homogeneity in the OCR accuracy across the corpus proved to be more important than having perhaps only a few works with higher accuracy and the rest available in a lower quality. In terms of the OCR process, this paper illustrates how it was possible to reduce the processing time at maximum quality of a single book of average length (ca. 500 pages) from a minimum of 20 hrs to an average of about 3 hrs (though theoretically nearly infinitely reducible). This was achieved by replacing a step-by-step OCR process with a fully automated pipeline system run on an arbitrary number of servers, breaking up the full process of OCRing one book into minimal tasks that can be handled simultaneously by multiple servers.

Ensemble Model of Attention Mechanism-Based DCGAN and Autoencoder for Noised OCR Classification

Optical Character Recognition (OCR) is a technology that converts images of text into machine-readable formats, essential for digitizing printed texts and enabling digital searches. Traditional OCR methods often struggle with variations in font styles and noise. This paper proposes an innovative approach to enhance OCR classification under challenging conditions by leveraging an ensemble model that combines an Attention Mechanism-Based Generative Adversarial Network (GAN) and an Autoencoder. The GAN generates synthetic data to mitigate the limitations of small datasets, while the autoencoder extracts robust features from noisy images. The model undergoes a two-phase training process, initially learning from the augmented dataset and then fine-tuning on a smaller, labeled dataset. Grad-CAM is used to demonstrate interpretability, highlighting the attention regions during predictions. Experimental results show significant improvements in OCR accuracy and robustness, validating the effectiveness of the proposed method in handling noise and limited training data.

Algorithms for connecting scientific names with literature in the Biodiversity Heritage Library via the Global Names Project and Catalogue of Life

Being able to quickly find and access original species descriptions is essential for efficiently conducting taxonomic research. Linking scientific name queries to the original species description is challenging and requires taxonomic intelligence because on average there are an estimated three scientific names associated with each currently accepted species, and many historical scientific names have fallen into disuse from being synonymized or forgotten. Additionally, non-standard usage of journal abbreviations can make it difficult to automatically disambiguate bibliographic citations and ascribe them to the correct publication. The largest open access resource for biodiversity literature is the Biodiversity Heritage Library (BHL), which was built by a consortium of natural history institutions and contains over 200,000 digitized volumes of natural history publications spanning hundreds of years of biological research. Catalogue of Life (CoL) is the largest aggregator of scientific names globally, publishing an annual checklist of currently accepted scientific names and their historical synonyms. TaxonWorks is an integrative web-based workbench that facilitates collaboration on biodiversity informatics research between scientists and developers. The Global Names project has been collaborating with BHL, TaxonWorks, and CoL to develop a Global Names Index that links all of these services together by finding scientific names in BHL and using the taxonomic intelligence provided by CoL to conveniently link directly to the page referenced in BHL. The Global Names Index is continuously updated as metadata is improved and digitization technologies advance to provide more accurate optical character recognition (OCR) of scanned texts. We developed an open source tool, “BHLnames,” and launched a restful application programming interface (API) service with a freely available Javascript widget that can be embedded on any website to link scientific names to literature citations in BHL. If no bibliographic citation is provided, the widget will link to the oldest name usage in BHL, which often is the original species description. The BHLnames widget can also be used to browse all mentions of a scientific name and its synonyms in BHL, which could make the tool more broadly useful for studying the natural history of any species.

SEDIQA: Sound Emitting Document Image Quality Assessment in a Reading Aid for the Visually Impaired.

For visually impaired people (VIPs), the ability to convert text to sound can mean a new level of independence or the simple joy of a good book. With significant advances in optical character recognition (OCR) in recent years, a number of reading aids are appearing on the market. These reading aids convert images captured by a camera to text which can then be read aloud. However, all of these reading aids suffer from a key issue—the user must be able to visually target the text and capture an image of sufficient quality for the OCR algorithm to function—no small task for VIPs. In this work, a sound-emitting document image quality assessment metric (SEDIQA) is proposed which allows the user to hear the quality of the text image and automatically captures the best image for OCR accuracy. This work also includes testing of OCR performance against image degradations, to identify the most significant contributors to accuracy reduction. The proposed no-reference image quality assessor (NR-IQA) is validated alongside established NR-IQAs and this work includes insights into the performance of these NR-IQAs on document images. SEDIQA is found to consistently select the best image for OCR accuracy. The full system includes a document image enhancement technique which introduces improvements in OCR accuracy with an average increase of 22% and a maximum increase of 68%.