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

OCR2SEQ represents an innovative advancement in Optical Character Recognition (OCR) technology, leveraging a multi-modal generative augmentation strategy to overcome traditional limitations in OCR systems. This paper introduces OCR2SEQ’s unique approach, tailored to enhance data quality for sequence-to-sequence models, especially in scenarios characterized by sparse character sets and specialized vocabularies. At the heart of OCR2SEQ lies a set of novel augmentation techniques designed to simulate realistic text extraction errors. These techniques are adept at generating diverse and challenging data scenarios, thereby substantially improving the training efficacy and accuracy of text-to-text transformers. The application of OCR2SEQ has shown notable improvements in data processing accuracy, particularly in sectors heavily dependent on OCR technologies such as healthcare and library sciences. This paper demonstrates the capability of OCR2SEQ to transform OCR systems by enriching them with augmented, domain-specific data, paving the way for more sophisticated and reliable machine learning interpretations. This advancement in OCR technology, as presented in the study, not only enhances the accuracy and reliability of data processing but also sets a new benchmark in the integration of augmented data for refining OCR capabilities.

Along with the times, the world of banking is also required to have growth in providing services to the public. The world of banking itself has a significant contribution in daily life. However, some deficiencies that arise due to the application of the procedures used are still often encountered. This situation can be seen from the number of customer self-registration data that is still done manually. Optical Character Recognition (OCR) technology on Citizenship Cards can be used to get the results of accuracy and speed and get the best reading results. The purpose of this study was to use Optical Character Recognition (OCR) technology in reading the Identity Card (KTP). The readings from OCR can be used to compare the size of the original, medium, and small images in color and grayscale images, so that the best results can be found in the processing of personal data on Identity Cards with Optical Character Recognition (OCR). This study resulted in the accuracy of reading grayscale Identity Card (KTP) data more accurately. Where the amount of 86.32% for the accuracy of the colored Identity Card (KTP) and 88.58% for the accuracy of the grayscale Identity Card (KTP).

Chinese Optical Character Recognition (OCR) technology is essential for digital transformation in Chinese regions, enabling automated document processing across various applications. However, Chinese OCR systems struggle with visually similar characters, where subtle stroke differences lead to systematic recognition errors that limit practical deployment accuracy. This study develops FLIP (Feedback Learning-based Intelligent Plugin), a lightweight post-processing plugin designed to improve Chinese OCR accuracy across different systems without external dependencies. The plugin operates through three core components as follows: UTF-8 encoding-based output parsing that converts OCR results into mathematical representations, error correction using information entropy and weighted similarity measures to identify and fix character-level errors, and adaptive feedback learning that optimizes parameters through user interactions. The approach functions entirely through mathematical calculations at the character encoding level, ensuring universal compatibility with existing OCR systems while effectively handling complex Chinese character similarities. The plugin’s modular design enables seamless integration without requiring modifications to existing OCR algorithms, while its feedback mechanism adapts to domain-specific terminology and user preferences. Experimental evaluation on 10,000 Chinese document images using four state-of-the-art OCR models demonstrates consistent improvements across all tested systems, with precision gains ranging from 1.17% to 10.37% and overall Chinese character recognition accuracy exceeding 98%. The best performing model achieved 99.42% precision, with ablation studies confirming that feedback learning contributes additional improvements from 0.45% to 4.66% across different OCR architectures.

Optical character recognition (OCR) technologies have known an effervescent development in last decade. Development was strongly influenced by the development of hardware, advance in image processing, and classification algorithms. There are multiple OCR technologies available, each of them based on different approaches, e.g., geometric processing or cognitive learning based on neural networks. One critical parameter for each of those approaches is execution time. In our opinion a very important percent of text used to be “OCRed” is coming from preprinted documents and forms, which are bounded by various regulations in layout and/or contained information. Based on this observation we argue that most of the characters that must be recognized have a similar layout, thus improvement of the processing performance can be obtained by creating classes of similar characters (blobs) based on geometric similarities, and performing OCR only on the representative blob from each class. In this paper we will present the architecture of an OCR technology based on a multilayer neural network. Performance improvement has been obtained using a blob classifier that groups characters in classes, and then perform OCR only on the representative blob from each class.

The healthcare industry continues to depend extensively on paper-based prescriptions, frequently transmitted through fax systems, to ensure compliance with stringent security and regulatory standards. This reliance introduces significant challenges to manual processing, which is often labor-intensive, error-prone, and inefficient, thereby increasing the risk of medication errors and compromising patient safety. Optical Character Recognition (OCR) technology offers a promising solution by automating the conversion of handwritten and printed prescription images into machine-readable text, thereby enhancing the accuracy and efficiency of healthcare workflows. This paper presents a detailed review of OCR methodologies, focusing on feature extraction, classification, and segmentation techniques that are critical for achieving high recognition accuracy in complex handwritten texts, such as medical prescriptions. By leveraging advanced pattern recognition approaches, including neural networks and hybrid models, OCR systems can significantly reduce manual effort and errors in prescription processing. This study emphasizes the importance of selecting relevant feature extraction methods and robust classification algorithms to handle the variability and noise inherent in re-faxed prescriptions, thereby improving the reliability of automated prescription recognition systems. This study aims to guide and update researchers and practitioners in developing efficient OCR solutions tailored to the healthcare domain, ultimately contributing to safer and more efficient medication administration processes.

To date, most optical character recognition (OCR) systems process binary document images, and the quality of the input image strongly affects their performance. Since a binarization process is inherently lossy, different algorithms typically produce different binary images from the same gray scale image. The objective of this research is to study effects of global binarization algorithms on the performance of OCR systems. Several binarization methods were examined: the best fixed threshold value for the data set, the ideal histogram method, and Otsu's algorithm. Four contemporary OCR systems and 50 hard copy pages containing 91,649 characters were used in the experiments. These pages were digitized at 300 dpi and 8 bits/pixel, and 36 different threshold values (ranging from 59 to 199 in increments of 4) were used. The resulting 1,800 binary images were processed by all four OCR systems. All systems made approximately 40% more errors from images generated by Otsu's method than those of the ideal histogram method. Two of the systems made approximately the same number of errors from images generated by the best fixed threshold value and Otsu's method.

The advances in Optical Character Recognition (OCR) technology over the past decade have enabled the development of many automatic document-processing systems capable of 99% correct recognition on printed text. However, similar advances in Cursive Script Recognition (CSR) technology have not been forthcoming due, principally, to the vast variability of human handwriting. This paper investigates a method by which the more reliable OCR technology can be used to improve the CSR performance in a form processing application. A novel method is proposed to link handwriting data to contextual cue words that have been automatically obtained from an OCR process. This information is then used to select appropriate 'focused' lexicons to achieve better CSR results. The method was tested on 30 forms that were filled by 10 different writers. The experimental results together with a comparison to the base line recognition performance are presented.

We examine the use of character image analysis coupled with contextual information in complex data gathering forms to identify and correct optical character recognition (OCR) system rejection and substitution errors. Segmented characters from a complex data gathering form are initially classified using an OCR engine based on a combination of Karhunen-Loeve transforms and a back-propagation neural network. Systems of equations are derived from the data gathering form to determine the values of characters rejected by the OCR engine and to verify the consistency of the data captured. If the OCR results for a single form are determined to be inconsistent with respect to the form's data relationships, a set of decision algorithms which incorporates a second neural network and uses additional character features is used to tag characters according to their likelihood of substitution error. Potential substitution errors are incrementally added to the set of OCR reject errors and are processed through dynamically selected systems of equations and search techniques which correct both error classes. We provide experimental results and determine the extent to which errors can be detected and corrected for various OCR error rates.

In this paper we present an end-to-end trainable optical character recognition (OCR) system for recognizing machine-printed text in Thai documents. The end-to-end OCR system is based on a script-independent methodology using hidden Markov models. Our system provides an integrated workflow beginning with annotation and transcription of training images to performing OCR on new images with models trained on transcribed training images. The efficacy of our end-to-end OCR system is demonstrated by rapidly configuring our OCR engine for the Thai script. We present experimental results on Thai documents to highlight the specific challenges posed by the Thai script and analyze the recognition performance as a function of amount of training data.

Optical character recognition (OCR) technology is widely used to convert scanned documents to text. However, historical books still remain a challenge for state-of-the-art OCR engines. This work proposes a new approach to the OCR of large bodies of text by creating an adaptive mechanism that adjusts itself to each text being processed. This approach provides significant improvements to the OCR results achieved. Our approach uses a modified hierarchical optical flow with a second-order regularization term to compare each new character with the set of super-symbols (character templates) by using its distance maps. The classification process is based on a hybrid approach combining measures of geometrical differences (spatial domain) and distortion gradients (feature domain).

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.

In recent years, with the increasing usage of digital media and advancements in deep learning architectures, most of the paper-based documents have been revolutionized into digital versions. These advancements have helped the state-of-the-art Optical Character Recognition (OCR) and digital mailroom technologies become progressively efficient. Commercially, there already exists end to end systems which use OCR and digital mailroom technologies for extracting relevant information from financial documents such as invoices. However, there is plenty of room for improvement in terms of automating and correcting post information extracted errors. This paper describes the user-involved, self-correction concept based on the sequence to sequence Neural Machine Translation (NMT) as applied to rectify the incorrectness in the results of the information extraction. Even though many efficient Post-OCR error rectification methods have been introduced in the recent past to improve the quality of digitized documents, they are still imperfect and demand improvement in the area of context-based error correction specifically for the documents involving sensitive information. This paper further illustrates the capability of sequence learning with the help of feedback provided during each cycle of training, yields relatively better results and have outsmarted the state-of-the-art OCR error correction methods.

Historical newspapers are invaluable resources that capture the cultural, social, economic, and political dimensions of their time, providing unique insights into past events and daily life. However, the potential of these archives remains underutilised due to the limitations of traditional research methods, which rely on laborious manual examination of individual pages or articles. Digital archives have begun to address this issue by enhancing accessibility, but the lack of effective tools for parsing and analysing the contents still restricts their utility for large-scale historical research. Optical Character Recognition (OCR) technology plays a foundational role in converting scanned images into searchable text. However, OCR alone cannot adequately handle the complexities of historical newspapers, which often feature degraded image quality, inconsistent typography, and intricate layouts. In parallel, the effective segmentation and ordering of newspaper contents is essential for generating well-structured and logically ordered data from specific newspaper sections. This paper focuses on the development of a pipeline that addresses these challenges, using the daily newspaper Le Sémaphore de Marseille as a case study (35,703 issues covering the period 1827 to 1944). The proposed system integrates layout analysis, OCR, and Generative AI-driven information extraction techniques to extract specific data elements from scanned images, namely ship arrivals data, and to store them in a machine-readable format for further analysis. This well-structured output enables historians to analyse historical trade patterns, economic trends, and regional interactions more efficiently and at a much larger scale. An evaluation of the key pipeline components demonstrates the effectiveness of the system, achieving an F1-score of 96% in paragraph segmentation and information extraction, while also highlighting the need for further improvement in the critical OCR component.

This study aimed to develop a technology to recognize and warehouse text data from a table containing technical documents relating to construction and plant projects. To this end, a table optical character recognition (OCR) technology was proposed to tag text data by recognizing the structure of the table and the context of the content in the table. For analysis, the table format was first classified into two patterns: T1 and T2. T1 refers to a table with only one step of the header, and T2 refers to a table with two phases of the header. The table OCR model extracts text in cell units of the table using the OpenCV engine after extracting data from the headers. A training model improves text recognition rate through a long short-term memory (LSTM)-based Tesseract OCR engine. Extracted data from the table were stored in the DB and output in CSV format. The confusion matrix was applied to verify the recognition accuracy of the extracted data, and as a result of the verification, the F-measure value of T1 was 96%, and T2 was 87%. Therefore, from the outcome of this study, it is expected that the automated management of tasks that hitherto relied solely on the engineer’s experience will subsequently contribute to reducing the workload and improving the productivity of the engineer in charge.KeywordsAutomatic conversion of table contentsTable OCROpenCVTesseract OCR

Optical Character Recognition (OCR) is a major computer vision task by which characters of image are detected and recognized by comparing to training set images. Process of detecting character is one of the perplexing tasks in computer vision. This is because of input image often not correctly aligned or because of noise. This paper presents a complete Optical Character Recognition (OCR) system which is worked for English character mostly for Calibri font. This system first corrects skew of image if input image is not correctly aligned followed by noise reduction from input image. This process is passed through line and character segmentation that are passed into the recognition module and recognize characters. By experimenting with a set of 50 images, average achievement is 92%, 98% is for Calibri font. Moreover, the developed technique is computationally efficient and requires less time than other Optical character recognition system.