Application of improved bp algorithm in handwritten english text recognition system

Optical Character Recognition (OCR) and Handwritten Text Recognition (HTR) are technologies that enable text recognition. The difference between OCR and HTR is one designed specifically for digital text and one designed for handwritten text. There are already various implementations of OCR and HTR online. However, such systems do not guarantee the systems are in premises. To solve this problem, the OCR and HTR system must be built from the scratch. The purpose of this research is to improve the recognition by separating the text whether it is a handwritten or a printed text, which will later be forwarded into the appropriate recognition system. An application program interface (API) was also created in order to finalize the classification system into real world usage. In this research, the classification system being developed using convolutional neural network (CNN) method. To be able to reach the highest accuracy of the classification system, the experimentation and improvement about hyperparameters, dataset format, data augmentation and analysis on 3 CNN architectures were conducted. In the end of this research, there are 2 architectures in a tight competition, one is VGG-16 with 90.63% accuracy and one is AlexNet with 90.17% accuracy on ideal data testing. However, AlexNet is chosen as the winner after the testing with real data.

Text recognition in natural scene images is a challenging problem in computer vision. Different than the optical character recognition (OCR), text recognition in natural scene images is more complex due to variations in text size, colors, fonts, orientations, complex backgrounds, occlusion, illuminations and uneven lighting conditions. In this paper, we propose a segmentation-free method based on a deep convolutional recurrent neural network to solve the problem of cursive text recognition, particularly focusing on Urdu text in natural scenes. Compared to the non-cursive scripts, Urdu text recognition is more complex due to variations in the writing styles, several shapes of the same character, connected text, ligature overlapping, stretched, diagonal and condensed text. The proposed model gets a whole word image as an input without pre-segmenting into individual characters, and then transforms into the sequence of the relevant features. Our model is based on three components: a deep convolutional neural network (CNN) with shortcut connections to extract and encode the features, a recurrent neural network (RNN) to decode the convolutional features, and a connectionist temporal classification (CTC) to map the predicted sequences into the target labels. To increase the text recognition accuracy further, we explore deeper CNN architectures like VGG-16, VGG-19, ResNet-18 and ResNet-34 to extract more appropriate Urdu text features, and compare the recognition results. To conduct the experiments, a new large-scale benchmark dataset of cropped Urdu word images in natural scenes is developed. The experimental results show that the proposed deep CRNN network with shortcut connections outperform than other network architectures. The dataset is publicly available and can be downloaded from <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://data.mendeley.com/datasets/k5fz57zd9z/1</uri> .

The study presents the results of the development and testing of deep learning neural network architectures, which demonstrate high accuracy rates in classifying neurophysiological data, in particular hemodynamic brain activation patterns obtained by functional near-infrared spectroscopy, during solving mathematical problems on spatial-numerical associations. The analyzed signal represents a multidimensional time series of oxyhemoglobin and deoxyhemoglobin dynamics. Taking the specificity of the fNIRS signal into account, a comparative analysis of 2 types of neural network architectures was carried out: (1) architectures based on recurrent neural networks: recurrent neural network with long short-term memory, recurrent neural network with long short-term memory with fully connected layers, bidirectional recurrent neural network with long short-term memory, convolutional recurrent neural network with long short-term memory; (2) architectures based on convolutional neural networks with 1D convolutions: convolutional neural network, fully convolutional neural network, residual neural network. Trained long short-term memory recurrent neural network architectures showed worse results in accuracy in comparison with 1D convolutional neural network architectures. Residual neural network (model_Resnet) demonstrated the highest accuracy rates in three experimental conditions more than 88% in detecting age-related differences in brain activation during spatial-numerical association tasks considering the individual characteristics of the respondents’ signal.

Abstract- The growing need for automation in the banking sector has accelerated the adoption of advanced technologies for processing high volumes of transactional data. One critical challenge is the digitization of handwritten banking documents such as cheques and application forms. Traditional Optical Character Recognition (OCR) systems often underperform with handwritten inputs due to inconsistent handwriting styles, noise, and poor scan quality. This project introduces a deep learning-based OCR system tailored for handwritten data extraction in banking documents. It employs a hybrid neural architecture combining Convolutional Neural Networks (CNNs) for feature extraction and Recurrent Neural Networks (RNNs) with attention mechanisms for accurate sequence prediction. The system accurately extracts essential fields—account numbers, payee names, amounts, and signatures—from handwritten cheques. To enhance recognition accuracy, preprocessing steps such as binarization, noise reduction, skew correction, and segmentation are applied. Post-processing techniques like error correction, contextual verification, and data validation ensure reliable and regulation-compliant output. The system is further optimized using standard cheque formats and field layouts to improve localization and minimize the need for large labeled datasets. Experimental results demonstrate notable improvements in accuracy, processing speed, and operational efficiency, significantly reducing manual intervention and human error. The system is scalable and adaptable, extending its use to other handwritten banking documents. In conclusion, the proposed deep learning-based OCR system offers a robust and intelligent solution for handwritten data extraction in banking, supporting the move toward paperless operations and secure digital transformation. Keywords— Handwritten OCR, Banking Automation, Deep Learning, CNN, Document Digitization, OCR, Data Extraction

Insects make up over 70% of the world's known species (Resh and Carde 2009). This is well represented in collections across the world, with the Natural History Museum's pinned insect collection alone making up nearly 37% of the museum's remarkable 80 million specimen collection. Thus, this extraordinary dataset is a major focus of digitisation efforts here at the Museum. While hardware developments have seen digitisation processes significantly improve and speed up (Blagoderov et al. 2017), we now concentrate on the latest software and explore whether machine learning can lend a bigger hand in accelerating our digitisation of pinned insects. Traditionally, the digitisation of pinned specimens involves the removal of labels (as well as any supplementary specimen miscellanies) prior to photographing the specimen. In order to document labels, this process is typically followed by additional photographs of labels as the label documentation is often obstructed by their stacking on a pin, the specimen and additional specimen material, or the pin itself. However, these steps not only slow down the process of digitisation but also increase the risk of specimen damage. This encouraged the team at the Natural History Museum to develop a novel setup that would bypass the need for removing labels during digitisation. This led to the development of ALICE (Angled Label Image Capture and Extraction) (Dupont and Price 2019). ALICE is a multi-camera setup designed to capture images of angled specimens, which allows users to get a full picture of a specimen in a collection, including that of the label and the text within. Specifically, ALICE involves four cameras angled at different viewpoints in order to capture label information, as well as two additional cameras providing a lateral and dorsal view of the specimen. By viewing all the images taken from one specimen simultaneously, we can obtain a full account of the labels and of the specimen, despite any obstructions. This setup notably accelerates parts of the digitisation process, sometimes by up to 7 times (Price et al. 2019). Furthermore, ALICE presents the opportunity to incorporate machine learning and computer vision techniques to create a software that automates the process of transcribing the information contained on labels. Automatically transcribing text (whether typed or handwritten) from label images, leads to the topic of Optical Character Recognition (OCR). Regardless of any obstructions to the labels, standard OCR methods will often fail at detecting text from these angled specimens if no preprocessing is done. This was emphasised in Bieniecki et al. (2007), which showed that some standard OCR algorithms were highly sensitive to geometric distortions such as bad angles. Therefore, in our latest ALICE software, we take on a 5-step approach that segments labels and merges them together using machine learning and computer vision, before turning to standard OCR tools to transcribe texts. Our 5-step framework is described as follows: Label segmentation with Convolutional Neural Networks (CNNs), Label corner approximation, Perspective transformation of label, followed by image registration with a given template, Label-image merging using an averaging technique, OCR on merged label. Label segmentation with Convolutional Neural Networks (CNNs), Label corner approximation, Perspective transformation of label, followed by image registration with a given template, Label-image merging using an averaging technique, OCR on merged label. While ALICE aims to reveal specimen labels using a multi-camera setup, we ask ourselves whether an alternative approach can also be taken. This takes us to the next phase of our digitisation acceleration research on smarter cameras with cobots (collaborative robots) and the associated software. We explore the potential of a single camera setup that is capable of zooming into labels. Where intelligence was incorporated post-processing with ALICE, using cobots, we can incorporate machine learning and computer vision techniques in-situ, in order to extract label information. This all forms the focus of our presentation.

In order to explore the application of deep learning (DL) and artificial intelligence (AI) technologies in art education, this work proposes and optimizes an innovative art creation system—Creative Intelligence Cloud (CIC). The system combines a deep generative adversarial network and convolutional neural network, aiming to enhance the automation level, consistency of artistic styles, and creation efficiency in art creation. This work first analyzes existing art creation methods. It points out the shortcomings of traditional systems in terms of image quality, style transfer, and computational performance, especially the application limitations in real teaching scenarios. Therefore, this work designs an art creation model optimized by DL and validates and evaluates it through extensive experiments. The experimental results show that CIC outperforms existing mainstream models in multiple dimensions, including image quality, computational performance, user experience, and style creation. For example, in image quality evaluation, CIC achieves high scores in clarity (0.89), detail performance (0.85), style consistency (0.87), and color accuracy (0.91). In terms of computational performance and resource consumption, CIC shows its superiority, with a training time of only 1500 s, memory consumption of 4.9GB, and a Graphics Processing Unit resource usage rate of 70%. Compared to models such as the Visual Perception Generative Adversarial Network and Artistic Recognition and Transfer Style Convolutional Neural Network, CIC is more efficient and consumes fewer resources. Furthermore, CIC’s scores in user experience and style transfer capability are significantly higher than those of other models, providing smoother and more creatively rich art creation tools for art education. Therefore, this work offers new ideas and methods for the application of DL and AI technologies in art creation and art education, and promotes the practical use of AI in art education. The work has certain academic contributions and practical value.

Most Latin word and character recognition systems have numerous classification algorithms to automate the identification of handwritten characters. However, despite extensive research on various Latin-based languages, relatively limited attention has been given to the recognition of handwritten text in Nigerian indigenous languages. Handwritten character recognition is challenging due to the variations in shape and style. In addition to that, these characters naturally vary among individuals. This work presents an offline character recognition system for Igbo handwritten alphabets using convolutional neural networks. In this study, a dataset comprising 9,000 character images was created, with 250 distinct samples for each of the 36 letters in the Igbo alphabet. Of these, 200 samples per character (a total of 7,200 images) were pre-processed, binarized, and normalized for training two Convolutional Neural Network (CNN) models. The remaining 50 samples per character (1,800 images) were reserved for testing. Model 1 and Model 2 achieved recognition accuracies of 83.5% and 85.0%, respectively. The proposed approach demonstrates potential for enhancing the automation and digitization of handwritten Igbo texts into machine-readable formats. Keywords: Optical Character Recognition, Igbo Handwritten Characters, Nigerian, Indigenous, Convolutional Neural Network Journal Reference Format: Woods, N.C. &amp; Oyedeji, O.A. (2025): Offline Handwritten Character Recognition for Igbo Alphabets Using Convolutional Neural Networks. Journal of Behavioural Informatics, Digital Humanities and Development Rese Vol. 11 No. 2. Pp 115-126 https://www.isteams.net/behavioralinformaticsjournal dx.doi.org/10.22624/AIMS/BHI/V11N2P11

Against the background of the new era, the birth of artificial intelligence technology opened a new chapter in human development. Artificial intelligence technology has been developed in many places. The report discusses the application and innovation of artificial intelligence technology in college sports. The first thing people think of artificial intelligence is robots. In fact, it can be said that artificial intelligence can replace human labor. Artificial intelligence is a product of modern technology and cannot be understood unilaterally. For example, the various means of transportation used in people’s daily travel is an artificial intelligence that can replace people’s walking. Another example is that elevators can replace people on stairs. It is also a type of artificial intelligence, which is not an advanced technology. Product, it is also seen everywhere in people’s daily life. Artificial intelligence is a synthesis of scientific and intelligent technology created by human beings. It is a scientific technology including computer science, cognition, logic, etc., formed through mutual intersection and integration. In recent years, artificial intelligence has achieved considerable development, but there are still a series of unsolved problems, and the development of artificial intelligence is still very long. This article studies what artificial intelligence has facilitated and changed the physical education in colleges and universities, and what changes have taken place in the teaching mode are all worthy of our thinking. As a result, artificial intelligence technology is convenient for teachers and students in teaching. Let’s take a look at how to innovate.

This research paper explores the hybrid models for Javanese character recognition using 15600 characters gathered from digital and handwritten sources. The hybrid model combines the merit of deep learning using convolutional neural networks (CNN) to involve feature extraction and a machine learning classifier using support vector machine (SVM). The dropout layer also manages overfitting problems and enhances training accuracy. For evaluation purposes, we also compared CNN models with three different architectures with multilayer perceptron (MLP) models with one and two hidden layer(s). In this research, we evaluated three variants of CNN architectures and the hybrid CNN-SVM models on both the accuracy of classification and training time. The experimental outcomes showed that the classification performances of all CNN models outperform the classification performances of both MLP models. The highest testing accuracy for basic CNN is 94.2% when using model 3 CNN. The increment of hidden layers to the MLP model just slightly enhances the accuracy. Furthermore, the hybrid model gained the highest accuracy result of 98.35% for classifying the testing data when combining model 3 CNN with the SVM classifier. We get that the hybrid CNN-SVM model can enhance the accuracy results in the Javanese characters recognition.

Sentiment analysis (SA) detects people’s opinions from text engaging natural language processing (NLP) techniques. Recent research has shown that deep learning models, i.e., Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), and Transformer-based provide promising results for recognizing sentiment. Nonetheless, CNN has the advantage of extracting high-level features by using convolutional and max-pooling layers; it cannot efficiently learn a sequence of correlations. At the same time, Bidirectional RNN uses two RNN directions to improve extracting long-term dependencies. However, it cannot extract local features in parallel, and Transformer-based like Bidirectional Encoder Representations from Transformers (BERT) are the computational resources needed to fine-tune, facing an overfitting problem on small datasets. This paper proposes a novel attention-based model that utilizes CNNs with LSTM (named ACL-SA). First, it applies a preprocessor to enhance the data quality and employ term frequency-inverse document frequency (TF-IDF) feature weighting and pre-trained Glove word embedding approaches to extract meaningful information from textual data. In addition, it utilizes CNN’s max-pooling to extract contextual features and reduce feature dimensionality. Moreover, it uses an integrated bidirectional LSTM to capture long-term dependencies. Furthermore, it applies the attention mechanism at the CNN’s output layer to emphasize each word’s attention level. To avoid overfitting, the Guasiannoise and GuasianDroupout are adopted as regularization. The model’s robustness is evaluated on four English standard datasets, i.e., Sentiment140, US-airline, Sentiment140-MV, SA4A with various performance matrices, and compared efficiency with existing baseline models and approaches. The experiment results show that the proposed method significantly outperforms the state-of-the-art models.

End-to-end Frameworks with Connectionist Temporal Classification (CTC) have achieved great success in text recognition. Despite high accuracies with deep learning, CTC-based text recognition methods also suffer from poor alignment (character boundary positioning) in many applications. To address this issue, we propose an end-to-end text recognition method based on robust prototype learning. In the new CTC framework, we formulate the blank as the rejection of character classes and use the one-vs-all prototype classifier as the output layer of the convolutional neural network. For network learning, based on forced alignment between frames and character labels, the most aligned frame is up-weighted in CTC training strategy to reduce estimation errors in decoding. Experiments of handwritten text recognition on four benchmark datasets of different languages show that the proposed method consistently improves the accuracy and alignment of CTC-based text recognition baseline.

Evaluating students through examination scripts in educational environments is crucial, particularly with 'Mastery Feedback' from educators, enhancing student understanding and self-regulation. However, it has remained a hectic exercise requiring some innovative solutions. This study proposes integrating robotics to automate recording and collating marked scripts to reduce the burden on lecturers and improve productivity. Key objectives include developing a data extraction pipeline using methods like Oriented FAST and Rotated BRIEF (O.R.B.) for image alignment and adaptive thresholding for lighting variations. Additionally, a character recognition model using a Single Input Convolutional Neural Network (SICNN) was designed with three preprocessing techniques—binarisation, thinning, and gradient magnitude calculation— tailored to different image requirements. Training on the 'EMNIST by_merge' dataset showed varied validation accuracies, with the gradient input SICNN model achieving the highest at 89.24% overall and the binary input SICNN model excelling with 99.39% on custom scripts. This approach aims to enhance educational administrative processes and efficiency and thus achieve sustainable education.

ABSTRACTIn recent years, object-based segmentation methods and shallow-model classification algorithms have been widely integrated for remote sensing image supervised classification. However, as the image resolution increases, remote sensing images contain increasingly complex characteristics, leading to higher intraclass heterogeneity and interclass homogeneity and thus posing substantial challenges for the application of segmentation methods and shallow-model classification algorithms. As important methods of deep learning technology, convolutional neural networks (CNNs) can hierarchically extract higher-level spatial features from images, providing CNNs with a more powerful recognition ability for target detection and scene classification in high-resolution remote sensing images. However, the input of the traditional CNN is an image patch, the shape of which is scarcely consistent with a given segment. This inconsistency may lead to errors when directly using CNNs in object-based remote sensing classification: jagged errors may appear along the land cover boundaries, and some land cover areas may overexpand or shrink, leading to many obvious classification errors in the resulting image. To address the above problem, this paper proposes an object-based and heterogeneous segment filter convolutional neural network (OHSF-CNN) for high-resolution remote sensing image classification. Before the CNN processes an image patch, the OHSF-CNN includes a heterogeneous segment filter (HSF) to process the input image. For the segments in the image patch that are obviously different from the segment to be classified, the HSF can differentiate them and reduce their negative influence on the CNN training and decision-making processes. Experimental results show that the OHSF-CNN not only can take full advantage of the recognition capabilities of deep learning methods but also can effectively avoid the jagged errors along land cover boundaries and the expansion/shrinkage of land cover areas originating from traditional CNN structures. Moreover, compared with the traditional methods, the proposed OHSF-CNN can achieve higher classification accuracy. Furthermore, the OHSF-CNN algorithm can serve as a bridge between deep learning technology and object-based segmentation algorithms thereby enabling the application of object-based segmentation methods to more complex high-resolution remote sensing images.

Text classification is a task to assign text documents according to its content to one or more classes automatically. Recently character-level models using deep neural networks have been developed to do classification text. Moreover, in some cases, character-level models have outperformed word-level models and traditional models, especially on user-generated dataset. The topologies that have been used for the character-level models are convolutional neural networks (CNN) and bidirectional recurrent neural networks (Bi-RNN), with its variants; long short-term memory (LSTM) and gated recurrent units (GRU). In this paper, CNN, Bi-RNN, and the combination of both are tested with character-level features and word-level features for text classification on English and Indonesian social media datasets. On small size datasets, word-level model outperformed character-level models. However, on dataset with millions of data, character-level model outperformed word-level model. Further analysis on the evaluation of word-level and character-level models is also discussed in this paper.

Handwriting text recognition, or htr, is a computer capability to receive and understand handwritten data from various sources, like paper journals and graphics, touchpad screen. Identification of handwritten text is a new and complicated field of study that has a vast range of applications in banks and other enterprises. In this work , we use a hybrid convolutional neural network (CNN) and Hybrid Bi-directional Long Short Term Memory (BLSTM) based Recurrent Neural Network design to determine text. We deploy CNN layers to create a variety of activation maps. Activation maps highlight the image's most important characteristics. This feature is then feed to BLSTM layer for encoding and decoding visual feature present in the input image .Our CNN-BLSTM based implementation is experimented with the dataset IAM to obtain the accuracy of handwritten text. We achieve an accuracy of 97.8% in IAM word dataset.