Text Recognition System Research Articles

Automatic Estimation of Age Distributions from the First Ottoman Empire Population Register Series by Using Deep Learning

Recently, an increasing number of studies have applied deep learning algorithms for extracting information from handwritten historical documents. In order to accomplish that, documents must be divided into smaller parts. Page and line segmentation are vital stages in the Handwritten Text Recognition systems; it directly affects the character segmentation stage, which in turn determines the recognition success. In this study, we first applied deep learning-based layout analysis techniques to detect individuals in the first Ottoman population register series collected between the 1840s and the 1860s. Then, we employed horizontal projection profile-based line segmentation to the demographic information of these detected individuals in these registers. We further trained a CNN model to recognize automatically detected ages of individuals and estimated age distributions of people from these historical documents. Extracting age information from these historical registers is significant because it has enormous potential to revolutionize historical demography of around 20 successor states of the Ottoman Empire or countries of today. We achieved approximately 60% digit accuracy for recognizing the numbers in these registers and estimated the age distribution with Root Mean Square Error 23.61.

OCR with the Deep CNN Model for Ligature Script-Based Languages like Manchu

Manchu is a low-resource language that is rarely involved in text recognition technology. Because of the combination of typefaces, ordinary text recognition practice requires segmentation before recognition, which affects the recognition accuracy. In this paper, we propose a Manchu text recognition system divided into two parts: text recognition and text retrieval. First, a deep CNN model is used for text recognition, using a sliding window instead of manual segmentation. Second, text retrieval finds similarities within the image and locates the position of the recognized text in the database; this process is described in detail. We conducted comparative experiments on the FAST-NU dataset using different quantities of sample data, as well as comparisons with the latest model. The experiments revealed that the optimal results of the proposed deep CNN model reached 98.84%.

Handwritten Word Recognition Using Fuzzy Matching Degrees

Abstract Handwritten text recognition systems interpret the scanned script images as text composed of letters. In this paper, efficient offline methods using fuzzy degrees, as well as interval fuzzy degrees of type-2, are proposed to recognize letters beforehand decomposed into strokes. For such strokes, the first stage methods are used to create a set of hypotheses as to whether a group of strokes matches letter or digit patterns. Subsequently, the second-stage methods are employed to select the most promising set of hypotheses with the use of fuzzy degrees. In a primary version of the second-stage system, standard fuzzy memberships are used to measure compatibility between strokes and character patterns. As an extension of the system thus created, interval type-2 fuzzy degrees are employed to perform a selection of hypotheses that fit multiple handwriting typefaces.

Recognition of Devanagari Scene Text Using Autoencoder CNN

Scene text recognition is a well-rooted research domain covering a diverse application area. Recognition of scene text is challenging due to the complex nature of scene images. Various structural characteristics of the script also influence the recognition process. Text and background segmentation is a mandatory step in the scene text recognition process. A text recognition system produces the most accurate results if the structural and contextual information is preserved by the segmentation technique. Therefore, an attempt is made here to develop a robust foreground/background segmentation(separation) technique that produces the highest recognition results. A ground-truth dataset containing Devanagari scene text images is prepared for the experimentation. An encoder-decoder convolutional neural network model is used for text/background segmentation. The model is trained with Devanagari scene text images for pixel-wise classification of text and background. The segmented text is then recognized using an existing OCR engine (Tesseract). The word and character level recognition rates are computed and compared with other existing segmentation techniques to establish the effectiveness of the proposed technique.

Recognition and Digitization of Handwritten Text using Histogram of Gradients and Artificial Neural Network

Handwriting recognition is one of the most persuasive and interesting projects as it is required in many real-life applications such as bank-check processing, postal-code recognition, handwritten notes or question paper digitization etc. Machine learning and deep learning methods are being used by developers to make computers more intelligent. A person learns how to execute a task by learning and repeating it over and over before it memorises the steps. The neurons in his brain will then be able to easily execute the task that he has mastered. This is also very close to machine learning. It employs a variety of architectures to solve various problems. Handwritten text recognition systems are models that capture and interpret handwritten numeric and character data from sources such as paper documents and photographs. For this application, a variety of machine learning algorithms were used. However, several limitations have been found, such as a large number of iterations, high training costs, and so on. Even though the other models have given impressive accuracy, it still has some drawbacks. In an unsupervised way, the Artificial Neural Network is used to learn effective data coding. For recognising real-world data, we built a model using Histogram of Oriented Gradients (HOG) and Artificial Neural Networks (ANN).

Challenges of Accent and vowels for Sindhi Speech Recognition System

While talking and writing in Sindhi language, many challenges are faced because of the large number of 52 characters or alphabets. Vowels and the accent keep changing in fluency of speaking and writing. Due to the different varities of languages in the world and the dearth of computer scientists in the field of Speech Recognition, it is considered difficult area of study and is the least advanced field of Artificial Intelligence. More specifically, the difficulties are faced in the speech recognition for languages like Arabic and its adapting languages such as Sindhi, Pashto, Urdu, and others. The script and sounds in every language are directly proportional to each other i.e. the shorter script has less sounds while the longer script has more sounds. We developed a system for speech to text recognition system for Sindhi language with the help of Sphinx model. We have also tested the different datasets through the input in various phases and compare the results and accuracy of the vowels and accents through the proposed system

RETRACTED ARTICLE: Effective offline handwritten text recognition model based on a sequence-to-sequence approach with CNN–RNN networks

Automatic text recognition system might serve as an important factor in creating a paperless environment through digitizing and processing the existing paper documents in the upcoming days. Handwritten recognition using deep learning methods has been widely explored by many researchers. The existence of large quantity of data and a variety of algorithmic innovations enable the ease of training deep neural networks. Different techniques have been initiated in the literature for recognizing text from handwritten documents. This paper proposes a hybrid handwritten text recognition (H2TR) model using deep neural networks that use the sequence-to-sequence (Seq2Seq) approach. This hybrid model makes use of the salient features of convolution neural network (CNN) and recurrent neural network (RNN) with long–short-term memory network (LSTM). It uses CNN to extract the features from the handwritten image. The features that are extracted are later modelled with a sequence-to-sequence approach and fed to RNN–LSTM for encoding the visual features and decoding the sequence of letters that are available in the handwritten image. The proposed model is tested with IAM and RIMES handwritten databases, which shows competitive letter accuracy and word accuracy results.

Deep Wavelet Neural Network based Robust Text Recognition for Overlapping Characters

This paper presents a deep learning based intelligent text recognition system with touching and overlapped characters. The robustness and effectiveness in the proposed model are enhanced through the modified configuration of neural network known as Deep Wavelet Neural Network (DWNN). The capability of deep learning networks to learn efficiently from an unlabeled dataset has attracted the attention of many researchers over the last decade. However, the performance of these networks is subject to the quality of the dataset and invariant image representation. Numerous optical character recognition techniques have also been presented in the recent years, but the overlapped and touching characters have not been addressed much. The nonlinear and uncertain representation of image data in case of overlapped text adds severe complexity in the process of feature extraction and respective learning. The proposed architecture of DWNN uses fast decaying wavelet functions as activation function in place of conventional sigmoid function to cope up with the uncertainties and nonlinearity of the data representation in overlapped text images. It comprises of cascaded layered architecture of translated and dilated versions of wavelets as activation functions for the training and feature extraction at multiple levels. The local transformation and deformation variation in the visual data has also been taken care efficiently through the modified architecture of DWNN. Comprehensive experimental analysis has been performed over various test images to verify the effectiveness of the proposed text recognition system. The performance of the proposed method is assessed with the help of the metrics, namely, estimation error, cost function and accuracy. The proposed approach will be implemented in MATLAB.

Transformer Based End-to-End Text Recognition System for Korean Handwritten Documents

Transformer Based End-to-End Text Recognition System for Korean Handwritten Documents

Research of the Handwriting Recognition Methods

This paper examines the methods for handwriting recognition. In the first part, the basic concept of the text recognition system is considered and the features of the operation of these systems are described, it also talks about possible problems in recognition that arise when working with text. The second part examines the difficulties in recognizing handwritten characters associated with the peculiarities of a language, style and handwriting recognition. The third part contains an analysis of methods for preliminary processing of images toimprove the quality of further segmentation and text recognition. The next section describes approaches to segmenting text in a document. The fifth section contains an analysis of some of the methods for classifying handwritten characters. This section talks about the principles of such methods as using templates, using outline models, and also attribute-based methods. The mathematical models and algorithms for each method are described. The conclusion summarizes the state of the handwriting recognition systems and provides a general algorithm for the system's operation in order of its further implementation based on the above analyses.

Towards the Natural Language Processing as Spelling Correction for Offline Handwritten Text Recognition Systems

The increasing portability of physical manuscripts to the digital environment makes it common for systems to offer automatic mechanisms for offline Handwritten Text Recognition (HTR). However, several scenarios and writing variations bring challenges in recognition accuracy, and, to minimize this problem, optical models can be used with language models to assist in decoding text. Thus, with the aim of improving results, dictionaries of characters and words are generated from the dataset and linguistic restrictions are created in the recognition process. In this way, this work proposes the use of spelling correction techniques for text post-processing to achieve better results and eliminate the linguistic dependence between the optical model and the decoding stage. In addition, an encoder–decoder neural network architecture in conjunction with a training methodology are developed and presented to achieve the goal of spelling correction. To demonstrate the effectiveness of this new approach, we conducted an experiment on five datasets of text lines, widely known in the field of HTR, three state-of-the-art Optical Models for text recognition and eight spelling correction techniques, among traditional statistics and current approaches of neural networks in the field of Natural Language Processing (NLP). Finally, our proposed spelling correction model is analyzed statistically through HTR system metrics, reaching an average sentence correction of 54% higher than the state-of-the-art method of decoding in the tested datasets.

Dynamic features based stroke recognition system for signboard images of Gurmukhi text

The computation of correct features is an essential phase for efficient data representation and benchmarked accuracy in text recognition systems. The offline text lacks dynamic information regarding the writing order or nature of trajectories of stroke. Recovery of drawing order technique helps to retrieve trajectory of a stroke. This information aids in computing dynamic feature vector based on chain codes or trajectory points for text recognition. The present work proposes a dynamic feature extraction approach based on recovery of drawing order to understand scene text in Indic script Gurmukhi. An inhouse dataset of strokes was obtained from 820 real time Gurmukhi signboard images. Stroke recognition was performed using Conv1D, SVM and HMM classifiers. Best recognition results were achieved using SVM and Conv1D as 82.88% and 84.67%. The major objective of present study is to propose dynamic features based recognition scheme for Indic scripts signboard images suitable for real-life applications.

Design and Implementation of English Text Recognition System under Robot Vision

The traditional methods of English letter visual recognition are machine learning and contour feature extraction. However, limited by the hardware resources such as camera and processor, it is difficult for the robot to realize fast and accurate text extraction and recognition. By comparing the results of domain average method, median filtering method and KNNF filtering method in text image preprocessing of robot, this paper proposes to use median filtering method for image preprocessing and corner detection method for text area extraction, which improves the efficiency of text image processing for robot. Based on the writing characteristics of English letters, a concentric rectangle tangent based on equal difference area is proposed The overall structure of the algorithm solves the problem of fast recognition of multi-directional mixed text, effectively reduces the influence of the angle between robot vision and pre recognition target on text recognition, and improves the speed and accuracy of text recognition by optimizing SOFM network. The system model has been verified based on Nao robot platform.

Urdu handwritten text recognition: a survey

Work on the problem of handwritten text recognition in Urdu script has been an active research area. A significant progress is made in this interesting and challenging field in the last few years. In this study, the authors presented a comprehensive survey for a number of offline and online handwritten text recognition systems for Urdu script written in Nastaliq font style from 2004 to 2019. Following features make their contribution worthwhile and unique among the reviews of a similar kind: (i) their review classifies the existing studies based on types of recognition systems used for Urdu handwritten text, (ii) it covers a very different outlook of the recognition process of the Urdu handwritten text at different granularity levels (e.g. character, word, ligature, or sentence level), (iii) this review article also presents each of surveyed articles in following dimensions: the task performed, its granularity level, dataset used, results obtained, and future dimensions, and (iv) lastly it gives the summary of the surveyed articles according to the granularity levels, publishing years, related tasks or subtasks, and types of classifiers used. In the end, major challenges and tasks related to Urdu handwritten text recognition approaches are also discussed in detail.

Scene text detection using enhanced Extremal region and convolutional neural network

Text in scene images usually contains significant information. Text detection and recognition in the scene is important for a variety of advanced machine vision applications, such as image and video retrieval, automotive assistance, and multilingual translation. In particular, most text recognition systems require texts to be localized in images beforehand and this is a significant demand. The purpose of this study is to provide a method to detect texts in natural images. The proposed approach combines advantages of extremal region, ER, methods and classification of convolutional neural network, CNN. This significantly reduces the false positives and increases the accuracy of detection. The method of sliding windows is employed with different sizes in order to determine text candidates. Extraction of enhanced ERs is performed in three consecutive stages on three distinct color channels, R, G, and B. Then, the results are combined together by an add method. After grouping, the word candidates are classified to two classes of text and non-text sections by a CNN classifier. By applying non-maximum suppression (NMS) algorithm to the same words, words with the highest probability are selected. The average values of accuracy, recall, precision and F-measure of the proposed text detection model on the ICDAR2013 database are 0.893, 0.962, 0.948, and 0.955, respectively. The optimal cut point of the proposed method is 0.648, which has the highest average accuracy, 91.93%. The AUC of ROC and PR diagrams for the proposed model are 0.851 and 0.718, respectively. These results of AUC for ROC and PR curves showed an outstanding enhancement in comparison with the best detection rate of previous methods. Experimental results on the ICDAR2011, ICDAR2013 and ICDAR2015 databases also demonstrate that our algorithm outperforms the state-of-the-art scene text detection methods.

Cursive-Text: A Comprehensive Dataset for End-to-End Urdu Text Recognition in Natural Scene Images.

Reading text in natural scene images is an active research area in the fields of computer vision and pattern recognition as text detection, text recognition and script identification are required. In this data article, a comprehensive dataset for Urdu text detection and recognition in natural scene images is presented and analysed. To develop the dataset, more than 2500 natural scene images were captured using a digital camera and a built-in mobile phone camera. Three separate datasets for isolated Urdu character images, cropped word images and end-to-end text spotting were developed. The isolated Urdu character and cropped word images dataset contain a much larger number of samples than existing Arabic natural scene text datasets. The Urdu text spotting dataset contains images with Urdu, English and Sindhi text instances. However, the focus has been given to the Urdu text instances. The ground truths for each image in the isolated character, cropped word or text spotting datasets are provided separately. The proposed datasets can be used to perform Urdu text detection and recognition or end-to-end recognition in natural scenes. These datasets can also be helpful to develop Arabic and Persian natural scene text detection and recognition systems, as Urdu is a derived language of these scripts and has many similar letters. The datasets can also be helpful to develop multi-language translation systems, which can facilitate foreign tourists to read and translate multilingual text in natural scene images. To evaluate the datasets, state-of-the-art machine learning and deep neural networks were used to build the text detection and recognition models, where the best classification accuracies are achieved. To the best of the authors’ knowledge, this is the first dataset proposed for Urdu text detection, recognition or end-to-end text recognition in natural scene images. The aim of this data article is to present a benchmark work in the field of document analysis and recognition.Computer ScienceComputer Vision and Pattern RecognitionTablesFiguresImagesText FilesUsing a digital camera with a 20 megapixels (MP) sensor, an iPhone with a 12 MP back camera and a Samsung mobile with a 16MP back camera.RawAnalyzedEnvironmental factors such as illuminations, blurring and lighting conditions were considered while capturing images. The focus was given to the text within an image.The images in the dataset were obtained from the advertisement banners, sign-boards along the road side and streets, shop name boards, text written on the passing vehicles and walls.The images provided in this dataset were collected in different cities of Sindh, Pakistan.Summarized data are hosted with the article.The datasets and their related files are hosted in a Mendeley public data repository.DOI: https://data.mendeley.com/datasets/k5fz57zd9z/1URL: http://dx.doi.org/10.17632/k5fz57zd9z.1

Deep optical character recognition: a case of Pashto language

Over the past decades, text recognition technologies have focused immensely on noncursive isolated scripts. A text recognition system for the cursive Pashto script will serve as a great contribution, allowing the traditional, cultural, and educational Pashto literature to be converted into machine-readable form. We propose the use of deep learning architectures based on the transfer learning for the recognition of Pashto ligatures. For recognition analysis and evaluation, the ligature images in the dataset are preprocessed by data augmentation techniques, i.e., negatives, contours, and rotated to increase the variation of each sample and size of the original dataset. Rich feature representations are automatically extracted from the Pashto ligature images using deep convolution layers of the convolution neural network (CNN) architectures using fine-tuned approach. Pretrained CNN architectures: AlexNet, GoogleNet, and VGG (VGG-16 and VGG-19) are used for classification by feeding the extracted features to a fully connected layer and a softmax layer. The proposed deep transfer-based learning has achieved phenomenal recognition rates for Pashto ligatures on benchmark FAST-NU Pashto dataset. An accuracy of 97.24%, 97.46%, and 99.03% is achieved using AlexNext, GoogleNet, and VGGNet architectures, respectively.

Nom document digitalization by deep convolution neural networks

Nom is an ancient script used in Vietnam until the current Latin-based Vietnamese alphabet became common, and a large number of ancient Nom documents are in existence. Due to the gradual degradation of Nom documents and a decrease in the number of scholars who can understand them, a system to digitalize Nom documents is urgently necessary. This paper presents a segmentation-based method for digitalizing Nom documents using deep convolution neural networks. Nom pages are preprocessed, segmented into isolated characters, and then recognized by a single-character OCR. The structure of the U-Net is applied to create segmentation maps and extract character regions from them. Subsequently, we propose coarse and fine combined classifiers to recognize each character pattern. The results by the best classifier are revised by a decoder using a langue model. The decoder is the same as the connectionist temporal classification decoder used in end-to-end text recognition systems. Compared with the traditional segmentation method using projection profiles and the Voronoi diagram (IoU = 81.23%), the segmentation method using the deep convolution neural network produces a better result (IoU = 92.08%) for detecting character regions. The proposed CNN models for recognizing segmented character patterns outperforms the traditional models using the modified quadratic discriminant function and the learning vector quantization with the recognition rate of 85.07%. The combination of coarse and fine classifiers, the training dataset with salt and pepper noises, and the attention layer are the key factors in the recognition rate improvement.

Study of the influence of lexicon and language restrictions on computer assisted transcription of historical manuscripts

State-of-the-art Handwritten Text Recognition (HTR) systems allow transcribers to speed-up the transcription of handwritten text images. These systems provide transcribers an initial draft transcription that can be corrected with less effort than transcribing the handwritten text images from scratch. Currently, even the draft transcriptions offered by the most advanced HTR systems contain errors. Therefore, the supervision of this draft by a human transcriber is still necessary to obtain the correct transcription of the handwritten text images. This supervision can be eased by using interactive and assistive transcription systems, where the transcriber and the automatic system cooperate in the amending process.In this paper, the draft transcription is provided by an HTR system based on Convolutional and Recurrent Neural Networks with Bidirectional Long-Short Term Memory units, and the assistive system is fed by lattices generated by using Weighted Finite State Transducers. The influence of the lexicon and language restrictions on the performance of our computer assisted transcription system is evaluated on three historical manuscripts.The transcriptions offered by the proposed HTR system present very low error rates for the studied historical manuscripts. However, our assistive transcription system without lexicon or language restrictions is able to provide an additional reduction on the human effort required to correct the transcriptions in more than 50% over the transcriptions offered by the HTR system.

Research of text recognition systems and data removal for ukrainian-­language documents

This article discusses the existing software, the main task of which is to extract information from digitized documents. From all the software was selected what is based on neural network technology and deep learning. To extract information from documents, manual work of personal computer operators can be used, which takes a long time and does not exclude the influence of the human factor, as well as digitization of documents with further processing in software based on the principle of subordination of documents to templates and rules, data processing speed and the need to make changes to the settings due to a change in the type of document. The article aims to investigate the existing software for extracting data from digital documents based on neural network technology, and their applicability to Ukrainian-language documents. To do this, a simple set of invoices was created and uploaded to the system. The development of a system for extracting information from digitized Ukrainian-language documents using neural networks will speed up data processing, provide an opportunity for their processing depending on the scope of the user of this software. It is established that at present, there are no systems that can independently determine what data is needed for extraction from Ukrainian-language documents. Existing systems require the creation of software that will act as a cover for the functionality of systems that transmit their information through the REST API. Google Form Parser is considered to be the best system, but it requires a constant connection to the Internet, which can be a serious obstacle to the use of such a product in certain areas of activity.