Character Recognition Method Research Articles

Detection and identification of un-uniformed shape text from blurred video frames

<p><span lang="EN-GB">The identification and recognition of text from video frames have received a lot of attention recently, that makes many computer vision-based applications conceivable. In this study, we modify the picture mask and the original identification of the mask region convolution neural network and permit detection in three levels, including holistic, sequence, and at the level of pixels. To identify the texts and determine the text forms, semantics at the pixel and holistic levels can be used. With masking and detection, existences of the character and the word are separated and recognised. In addition, text detection using the results of 2-D feature space instance segmentation is done. Moreover, we explore text recognition using an attention-based optical character recognition (OCR) method with mask</span><span lang="EN-US"> r</span><span lang="EN-GB">egion convolution neural networks (R-CNN) to address and detect the problem of smaller and blurrier texts at the sequential level. Using attribute maps of the word occurrences in sequence to seq, the OCR method calculates the character sequence. At last, a fine-grained learning strategy is proposed to constructs models at word level using the annotated datasets, resulting in the training of a more precise and reliable model. The well-known benchmark datasets ICDAR 2013 and ICDAR 2015 are used to test our suggested methodology.</span></p>

Projection segmentation-based image recognition technology for automatic reading of gas meter

In view of the shortcomings of the existing gas meter reading methods, this paper introduces an automatic reading method and calibration device based on the projection segmentation method, which uses the color difference between the character part and the rest part of the last code wheel of the gas meter counter to realize image recognition of the turned characters, and then calculates the cumulative volume indication of gas meter based on the number of turned characters. The pixel projection value scanned by the camera device at the horizontal centerline of the last code wheel changes alternately when the code wheel rotates. The proposed projection segmentation method does not require recognition of specific characters, simplifying the algorithm and making it suitable for most calibration devices. Experiments show that the accuracy rate of the proposed method is 100% even under low-light conditions, which is a great improvement compared with the traditional character recognition method. Additionally, the reading resolution of the proposed method is improved by 10 times compared with the existing photoelectric sampling method and template matching method, and the total calibration time can be reduced by 6.7%–58.7%, which significantly enhances the calibration efficiency.

Chip Surface Character Recognition Based on OpenCV

Chip surface character recognition is an important part of quality inspection in the field of microelectronics manufacturing. By recognizing the character information on the chip, automated production, quality control, and data collection and analysis can be achieved. This article studies a chip surface character recognition method based on the OpenCV vision library. Firstly, the obtained chip images are preprocessed. Secondly, the template matching method is used to locate the chip position. In addition, the surface characters on the chip are individually segmented, and each character image is extracted separately. Finally, a Support Vector Machine (SVM) is used to classify and recognize characters. The results show that this method can accurately recognize the surface characters of chips and meet the requirements of chip quality inspection.

Vehicle License Plate Detection and Recognition using OpenCV and Tesseract OCR

License plate recognition (LPR) is essential as the number of vehicles increases and the human ability to accomplish this task is limited. If human labor is used to manage these, it will take a lot of time and energy and cause a discrepancy. License Plate Recognition (LPR) is an advanced technology that leverages optical character recognition (OCR) and various image processing methods to read vehicle license plates automatically. Typically, an LPR system comprises two primary components: detecting vehicles and their license plates and recognizing the alphanumeric characters displayed on those plates. This study explores the use of OpenCV for license plate detection and Tesseract OCR for character recognition. In this research, the dataset for training and testing the system included 100 license plates evenly split between plates featuring English and Lao characters. The Lao license plates presented unique complexities due to their specific characteristics. The experimental setup involved processing images of license plates taken from multiple angles. The system's performance was evaluated based on the speed and accuracy of line and character recognition. For English character plates, the recognition process took 0.12 seconds with an accuracy of 98.8%. In contrast, the Lao character plates required 0.24 seconds, achieving an accuracy rate of 89.42%.

Novel Deep Learning Application: Recognizing Inconsistent Characters on Pharmaceutical Packaging

Background Machine vision faces significant challenges when applied to text recognition on cardboard packaging particularly due to multiple printing methods, irregular character shapes, and curved packaging surfaces. Methods This research introduces a novel deep learning application for recognizing binarized expiration date and batch code characters printed using multiple printing methods. The method, based on Region-based Convolutional Neural Networks (R-CNN), enables character recognition directly from in the images without the need for extracting handcrafted features. In detail, this approach performs character recognition by using the whole image as input, extracting and learning salient character features directly from the packaging surface images. Results The R-CNN model, with a precision of 91.1% and an F1 score of 80.9%, effectively recognizes manufacturing markings on pharmaceutical packages, with inconsistencies in the characters’ shapes. In a comparative experiment using the same dataset of images, the R-CNN model significantly outperformed Tesseract OCR, achieving much higher precision, recall, and F1 scores. Conclusions The results of this study reveal that the deep learning method outperforms the well-established optical character recognition method in recognizing text characters printed with different printing methods. Presented in this study, the deep learning method recognizes text characters with high precision. It is also suitable for recognizing text printed on curved surfaces, provided proper preprocessing is applied. The problem investigated in the study differs from previous research in the field, focusing on the recognition of texts printed with different printing methods. The research thus fills a gap in text recognition that existed in the research of the field. Furthermore, the study presents new ideas that will be utilized in our future research.

TRAFFIC VIOLATION PREDICTION USING DEEP LEARNING BASED ON HELMETS WITH NUMBER PLATE RECOGNITION

At the moment, two-wheelers are the most widely used kind of transportation. It is highly advised that both bike riders and soldiers wear helmets. Many academics are interested in object tracking in video surveillance, which is an important application and burgeoning field of study in image processing and machine learning. Finding objects in an image with a bounding box and different categories or shapes of the objects placed is called object detection. This study reviews tracking techniques, classifies them into several categories, and concentrates on significant and practical tracking approaches. After reviewing broad strategies under a scan of the literature on various methodologies, we analyze potential research areas. This study uses the YOLOv8 algorithm, an image processing technique, to identify motorcycle riders who do not wear helmets. Additionally, put the Optical Character Recognition method into practice to identify the license plate in a picture and retrieve user information. Next, determine the fine amount. Eventually, SMS services will be able to notify consumers in order to prevent motorbike accidents. We evaluate the framework in terms of speed and accuracy.

Datasets and annotations for layout analysis of scientific articles

For a long time now, datasets containing scientific articles have been crucial to the analysis and recognition of document images. These document collections have frequently served as a testing ground for cutting-edge methods for optical character recognition, layout analysis, and document understanding in general. We thoroughly analyze and compare many datasets proposed for layout analysis of scientific documents, ranging from small collections of scanned papers to modern large-scale datasets containing digital-born papers, which have been proposed to train deep learning-based methods. Furthermore, we outline a detailed taxonomy of the annotation procedures used considering manual, automatic, and generative approaches, and we analyze their benefits and drawbacks. This survey is meant to provide the reader with a review of the most used benchmarks together with detailed information on data, annotations, and complexity, helping scholars to identify the most suitable dataset for their tasks of interest. We also discuss possible open problems to further enhance datasets to support research in the layout analysis of scientific articles.

An Unsupervised Character Recognition Method for Tibetan Historical Document Images Based on Deep Learning

As there is a lack of public mark samples of Tibetan historical document image characters at present, this paper proposes an unsupervised Tibetan historical document character recognition method based on deep learning (UD-CNN). Firstly, using the Tibetan historical document character component, the Tibetan historical document character sample data set is constructed for model-aided training. Then, the character baseline information is introduced, and a fine-grained feature learning strategy is proposed. For the samples above and below the baseline, the Up-CNN recognition model and Down-CNN recognition model are established. The convolution neural network model is trained and optimized for the samples above and below the baseline, respectively, to improve the recognition accuracy. The experimental results show that the proposed method obviously affects the unmarked character classification and recognition of real Tibetan historical document images. The recognition rate of Top5 can reach 92.94%, and the recognition rate of Top1 can be increased from 82.25% to 87.27% using the CNN model only.

Advanced approach for Moroccan administrative documents digitization using pre-trained models CNN-based: character recognition

In the digital age, efficient digitization of administrative documents is a real challenge, particularly for languages with complex scripts such as those used in Moroccan documents. The subject matter of this article is the digitization of Moroccan administrative documents using pre-trained convolutional neural networks (CNNs) for advanced character recognition. This research aims to address the unique challenges of accurately digitizing various Moroccan scripts and layouts, which are crucial in the digital transformation of administrative processes. Our goal was to develop an efficient and highly accurate character recognition system specifically tailored for Moroccan administrative texts. The tasks involved comprehensive analysis and customization of pre-trained CNN models and rigorous performance testing against a diverse dataset of Moroccan administrative documents. The methodology entailed a detailed evaluation of different CNN architectures trained on a dataset representative of various types of characters used in Moroccan administrative documents. This ensured the adaptability of the models to real-world scenarios, with a focus on accuracy and efficiency in character recognition. The results were remarkable. DenseNet121 achieved a 95.78% accuracy rate on the Alphabet dataset, whereas VGG16 recorded a 99.24% accuracy on the Digits dataset. DenseNet169 demonstrated 94.00% accuracy on the Arabic dataset, 99.9% accuracy on the Tifinagh dataset, and 96.24% accuracy on the French Special Characters dataset. Furthermore, DenseNet169 attained 99.14% accuracy on the Symbols dataset. In addition, ResNet50 achieved 99.90% accuracy on the Character Type dataset, enabling accurate determination of the dataset to which a character belongs. In conclusion, this study signifies a substantial advancement in the field of Moroccan administrative document digitization. The CNN-based approach showcased in this study significantly outperforms traditional character recognition methods. These findings not only contribute to the digital processing and management of documents but also open new avenues for future research in adapting this technology to other languages and document types.

Development of Artificial Intelligence Image Classification Models for Determination of Umbilical Cord Vascular Anomalies.

The goal of this work was to develop robust techniques for the processing and identification of SUA using artificial intelligence (AI) image classification models. Ultrasound images obtained retrospectively were analyzed for blinding, text removal, AI training, and image prediction. After developing and testing text removal methods, a small n-size study (40 images) using fastai/PyTorch to classify umbilical cord images. This data set was expanded to 286 lateral-CFI images that were used to compare: different neural network performance, diagnostic value, and model predictions. AI-Optical Character Recognition method was superior in its ability to remove text from images. The small n-size mixed single umbilical artery determination data set was tested with a pretrained ResNet34 neural network and obtained and error rate average of 0.083 (n = 3). The expanded data set was then tested with several AI models. The majority of the tested networks were able to obtain an average error rate of <0.15 with minimal modifications. The ResNet34-default performed the best with: an image-classification error rate of 0.0175, sensitivity of 1.00, specificity of 0.97, and ability to correctly infer classification. This work provides a robust framework for ultrasound image AI classifications. AI could successfully classify umbilical cord types of ultrasound image study with excellent diagnostic value. Together this study provides a reproducible framework to develop AI-specific ultrasound classification of umbilical cord or other diagnoses to be used in conjunction with physicians for optimal patient care.

An optimizing method of Japanese character recognition based on improved support vector machine

An optimizing method of Japanese character recognition based on improved support vector machine

Application of OCR-based assistance solutions in engine maintenance

The aviation industry is one of the leading transportation sectors with a rising number of passengers worldwide. However, this rise in demand leads to increased maintenance requirements for the engines. Jet engines are comprised of many components each denoted with a part and serial number. The data entry task for mechanics can be cumbersome and human errors can lead to incorrectly documented numbers and even result in severe safety issues. To assist mechanics in the task of recognizing and transcribing serial numbers, optical character recognition methods are being considered, with no satisfactory solution being found yet. This paper addresses this issue by comparing possible optical character recognition methods and identifying ways to improve the error rate based on a real use case.

Research and evaluation of the efficiency of handwritten character recognition methods using convulsional neural networks

The paper analyzes the possibilities of using deep learning neural networks for the implementation of text processing information systems, substantiates the prospects of this technology and the possibilities of its improvement. The possibility of using the MNIST database of handwritten digits on, as well as the EMNIST database of handwritten letters and numbers, namely the EMNIST Letters set, was considered. The research object was modelled in IDEF0 and IDEF3 notations for the «AS-IS» option. It was found that «Building a dataset for model training» and «Choosing a convolutional neural network architecture» are the most frequently asked questions. Reengineering measures are proposed, namely, the expediency of using, in addition to the well-known EMNIST and MNIST sets, a set of handwritten and italic fonts with Ukrainian glyphs, additionally created as part of the work, is shown. For this purpose, modern IT tools such as the Pillow library, Image Data Generator and the Scikit-Learn package were used to select training and test samples. Also, in addition to the initially proposed simplest CNN architectures of the Lenet type, the use of more complex architectures of the AlexNet and VGG-16 types is proposed. Taking into account the proposed reengineering measures, IDEF0 and IDEF3 diagrams were constructed for the «TO-BE» option. The paper analyzes in detail the results of recognizing handwritten Ukrainian letters and Arabic numerals using 6 different CNN architectures using a synthetic data set for training. The research presented in the work was carried out using a software application developed in the Python programming language using the Scikit Learn package, which provides the user with the ability to recognize handwritten text using a multilayer perceptron. carried out precisely using the developed program. It is justified that, in contrast to simple Lenet-type architectures, it is more appropriate to use more complex options, namely the VGG-16 type architecture. Experimental studies of the influence of the number of CNN parameters of different architectures on the recognition accuracy and training time of the neural network have been carried out. Also analyzed are the results of character recognition when recognizing images that do not belong to the training or test sample

SideNet: Learning representations from interactive side information for zero-shot Chinese character recognition

Existing methods for zero-shot Chinese character recognition usually exploit a single type of side information such as radicals, glyphs, or strokes to establish a mapping with the input characters for the recognition of unseen categories. However, these approaches have two limitations. Firstly, the mappings are inefficient owing to their complexity. Some existing methods design radical-level mappings using a non-differentiable dictionary-matching strategy, whereas others construct sophisticated embeddings to map seen and unseen characters into a unified latent space. Although the latter approach is straightforward, it lacks a learnable scheme for explicit structure construction. Secondly, the complementarity within multiple types of side information has not been effectively explored. For example, the radicals provide structural knowledge at an abstract level, whereas glyphs offer detailed information on their figurative counterparts. To this end, we propose a new method called SideNet that jointly learns character-level representations assisted by two types of interactive side information: radicals and glyphs. SideNet contains a structural conversion module that extracts radical knowledge via dimensional decomposition, and a spatial conversion module that encodes the radical counting map to produce an interactive outcome between radicals and glyph. Finally, we propose a new classifier that integrates the converted features by a similarity-guided fusion mechanism. To the best of our knowledge, this study represents the first attempt to integrate these two types of side information and explore a joint representation for zero-shot learning. Experiments show that SideNet consistently outperforms existing methods by a significant margin in diverse scenarios, including handwriting, printed art, natural scenes, and ancient Chinese characters, which demonstrates the potential of joint learning with multiple types of side information.

Recognition of Arabic Air-Written Letters: Machine Learning, Convolutional Neural Networks, and Optical Character Recognition (OCR) Techniques

Air writing is one of the essential fields that the world is turning to, which can benefit from the world of the metaverse, as well as the ease of communication between humans and machines. The research literature on air writing and its applications shows significant work in English and Chinese, while little research is conducted in other languages, such as Arabic. To fill this gap, we propose a hybrid model that combines feature extraction with deep learning models and then uses machine learning (ML) and optical character recognition (OCR) methods and applies grid and random search optimization algorithms to obtain the best model parameters and outcomes. Several machine learning methods (e.g., neural networks (NNs), random forest (RF), K-nearest neighbours (KNN), and support vector machine (SVM)) are applied to deep features extracted from deep convolutional neural networks (CNNs), such as VGG16, VGG19, and SqueezeNet. Our study uses the AHAWP dataset, which consists of diverse writing styles and hand sign variations, to train and evaluate the models. Prepossessing schemes are applied to improve data quality by reducing bias. Furthermore, OCR character (OCR) methods are integrated into our model to isolate individual letters from continuous air-written gestures and improve recognition results. The results of this study showed that the proposed model achieved the best accuracy of 88.8% using NN with VGG16.

Deep learning-based text detection and recognition on architectural floor plans

An important aspect of automatic floor plan analysis is the extraction of textual information, as it is essential for a thorough understanding of the drawing. This paper presents a text extraction approach utilizing a deep learning-based object detection model and state-of-the-art Optical Character Recognition (OCR) methods. The paper contributes to the research community in three ways: First, it introduces additional annotations to existing data sets to encompass text elements. Second, it proposes a specialized data synthesis pipeline, allowing for generating training images that mimic important characteristics of real data. Finally, it documents a comparative study of deep learning-based object detection architectures (Tesseract, EAST, CRAFT, Faster R-CNN, YOLOv5, YOLOR, YOLOv7, and YOLOv8) and OCR tools (PARSEq, MATRN, EasyOCR, and Tesseract) for the task. Results indicate that YOLOv7 yields the best text detection performance (up to 97.5% wmAP) and PARSEq excels in character recognition (85.2% CER). The data sets are made available.

Sistem Pemantauan Slot Parkir Menggunakan Sensor Ultrasonik JSN-SR04T dan Pengenalan Plat Nomor Kendaraan dengan ESP32-CAM

A parking slot monitoring system prototype has been produced using the JSN-SR04T ultrasonic sensor and vehicle license plate recognition with ESP32-CAM. The system was created to make it easier for motorists to monitor the availability of parking slots remotely by utilizing Telegram which is connected to the ESP32-CAM module and Arduino Mega 2560. The ultrasonic sensor detects the distance of vehicles entering or exiting the parking lot, then a servo motor opens the entry and exit bars. Vehicle users can monitor the availability of parking slots on the Telegram bot. In each slot there is an ultrasonic sensor that detects the distance so that it can find out whether there is a vehicle in the slot. The test results show that the ultrasonic sensor has an average error percentage of 0.65%. The parking barrier can be opened when the ultrasonic sensor detects the presence of a vehicle at the entrance or exit and the ultrasonic sensor can detect the presence of a vehicle according to the conditions in the slot. The system is equipped with vehicle license plate character recognition using the Optical Character Recognition (OCR) method. Through the ESP32-CAM module camera webserver, the OCR program can detect vehicle plates with the furthest distance of 140 cm using video resolution (400x296) and 300 cm using video resolution (1600x1200). The OCR program can read the vehicle plate characters correctly and the results for the number of characters obtained correspond to the license plate being tested, then the vehicle plate data is stored in the database

AI Based Tamil Palm Leaf Character Recognition

A brand-new character recognition method has been created especially for Tamil manuscripts written on palm leaves. A variety of preprocessing techniques are used to obtain reliable recognition because these manuscripts are complicated and have age-related deterioration. Using cutting-edge image processing techniques, manuscript photos are enhanced and preprocessed in the earliest stage to improve clarity. Then, in accordance with the distinctive arrangement of these historical artifacts, these photos are divided into three separate portions. After segmentation, these parts are converted to grayscale to create the ideal contrast needed for character detection. Noise canceling algorithms have been incorporated to prevent any distortions or degradations that may occur as a result of the age of the manuscripts or other environmental influences. After this mitigation, the photos are binarized to emphasize the isolation of the figures from their surroundings. This makes sure that each character stands out clearly, laying the groundwork for the crucial next step: segmenting individual characters. The foundation of the training phase is this segmentation. Convolutional neural networks (CNNs), which excel at handling image-based tasks, were incorporated into the deep learning architecture used for model building. Utilizing a sizable dataset compiled from numerous articles, the model underwent intensive training. As a result, the model was able to recognise characters from these texts with an astounding accuracy rate of 89%. With the help of Flask, the complete system has been easily integrated into a user-friendly web interface. This platform's goal is quite clear: fusing the elegance and profundity of ancient scripts with the effectiveness of contemporary technology. It is positioned as a crucial tool for both academic research and teaching purposes. By doing this, it guarantees that the priceless history and knowledge found in these manuscripts remain accessible and lays the groundwork for their preservation for future generations. Keywords— Character recognition, Tamil palm manuscripts, Preprocessing, Visual clarity, Grayscale conversion, Noise cancellation, Binarization, Segmentation, Training, Flask-based web interface, Research, Education.

From leaves to labels: Building modular machine learning networks for rapid herbarium specimen analysis with LeafMachine2.

Quantitative plant traits play a crucial role in biological research. However, traditional methods for measuring plant morphology are time consuming and have limited scalability. We present LeafMachine2, a suite of modular machine learning and computer vision tools that can automatically extract a base set of leaf traits from digital plant data sets. LeafMachine2 was trained on 494,766 manually prepared annotations from 5648 herbarium images obtained from 288 institutions and representing 2663 species; it employs a set of plant component detection and segmentation algorithms to isolate individual leaves, petioles, fruits, flowers, wood samples, buds, and roots. Our landmarking network automatically identifies and measures nine pseudo-landmarks that occur on most broadleaf taxa. Text labels and barcodes are automatically identified by an archival component detector and are prepared for optical character recognition methods or natural language processing algorithms. LeafMachine2 can extract trait data from at least 245 angiosperm families and calculate pixel-to-metric conversion factors for 26 commonly used ruler types. LeafMachine2 is a highly efficient tool for generating large quantities of plant trait data, even from occluded or overlapping leaves, field images, and non-archival data sets. Our project, along with similar initiatives, has made significant progress in removing the bottleneck in plant trait data acquisition from herbarium specimens and shifted the focus toward the crucial task of data revision and quality control.

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.