Symbol Recognition Research Articles

Mathematical and neuro-mathematical connections activated by a teacher and his student in the geometric problems-solving: A view of networking of theories

The research goal is twofold: to articulate neuro-mathematics with the extended theory of mathematical connections that uses onto-semiotic approach tools and to explore the connections established by a teacher and his student when solving a problem about the volume of two boxes, one of toothpaste and the other of tomato. This research was developed in two stages: the theories were articulated assuming concordances and complementarities, highlighting the notion of connection, and a context of reflection was considered carried out in three phases where the participants were selected, participant observation was carried out in the classroom during solving a problem and then analyzing the data with the new tool to explore mathematical and neuro-mathematical connections. The findings present the mathematical connections established by the teacher and the student of meaning, feature, procedural, different representations (alternate, equivalent, and from a horizontal mathematization view), and part-whole, as well as neuro-mathematical connections of: recognition of terms and symbols; visual perception, spatial skills and motor coordination; association of mathematical concepts and formulas; intermediate calculations and unit conversion; solve operations step by step and understand the process; verification and conclusion, activated in the brain areas linked to each mathematical practice sequentially.

Application of neural network for automatic symbol recognition in production of electronic navigation charts from paper charts

Abstract This research boarded on a novel initiative to replace the error-prone and labour-intensive process of converting Paper Nautical Chart (PNC) symbols to Electronic Navigational Chart (ENC) symbols with a more efficient and automated manner using Artificial Intelligence (AI). The proposed method applies the Convolutional Neural Network and YOLOv5 model to recognise and convert symbols from PNC into their corresponding ENC formats. The model's competence was evaluated with performance metrics including Precision, Recall, Average Precision, and mean Average Precision. Among the different variations of the YOLOv5 models tested, the YOLOv5m version revealed the best performance achieving a mean Average Precision of 0 ⋅ 837 for all features. A confusion matrix was used to visualise the model's classification accuracy for various chart symbols, underlining strengths and identifying areas for improvements. While the model has demonstrated high ability in identifying symbols like ‘Obstruction’ and ‘Major/Minor Lights’, it exhibited lesser accuracy with ‘Visible Wreck’ and ‘Background’ categories. Further, the developed graphical user interface (GUI) allowed users to interact with the artificial neural network model without demanding detailed knowledge of the underlying programming or model architecture.

Optical Medieval Music Recognition—A Complete Pipeline for Historic Chants

Manual transcription of music is a tedious work, which can be greatly facilitated by optical music recognition (OMR) software. However, OMR software is error prone in particular for older handwritten documents. This paper introduces and evaluates a pipeline that automates the entire OMR workflow in the context of the Corpus Monodicum project, enabling the transcription of historical chants. In addition to typical OMR tasks such as staff line detection, layout detection, and symbol recognition, the rarely addressed tasks of text and syllable recognition and assignment of syllables to symbols are tackled. For quantitative and qualitative evaluation, we use documents written in square notation developed in the 11th–12th century, but the methods apply to many other notations as well. Quantitative evaluation measures the number of necessary interventions for correction, which are about 0.4% for layout recognition including the division of text in chants, 2.4% for symbol recognition including pitch and reading order and 2.3% for syllable alignment with correct text and symbols. Qualitative evaluation showed an efficiency gain compared to manual transcription with an elaborate tool by a factor of about 9. In a second use case with printed chants in similar notation from the “Graduale Synopticum”, the evaluation results for symbols are much better except for syllable alignment indicating the difficulty of this task.

Investigating the crowding effect on letters and symbols in deaf adults

Reading requires the transformation of a complex array of visual features into sounds and meaning. For deaf signers who experience changes in visual attention and have little or no access to the sounds of the language they read, understanding the visual constraints underlying reading is crucial. This study aims to explore a fundamental aspect of visual perception intertwined with reading: the crowding effect. This effect manifests as the struggle to distinguish a target letter when surrounded by flanker letters. Through a two-alternative forced choice task, we assessed the recognition of letters and symbols presented in isolation or flanked by two or four characters, positioned either to the left or right of fixation. Our findings reveal that while deaf individuals exhibit higher accuracy in processing letters compared to symbols, their performance falls short of that of their hearing counterparts. Interestingly, despite their proficiency with letters, deaf individuals didn’t demonstrate quicker letter identification, particularly in the most challenging scenario where letters were flanked by four characters. These outcomes imply the development of a specialized letter processing system among deaf individuals, albeit one that may subtly diverge from that of their hearing counterparts.

A CNN-KNN Based Recognition of Online Handwritten Symbols within Physics Expressions Using Contour-Based Bounding Box (CBBS) Segmentation Technique

A CNN-KNN Based Recognition of Online Handwritten Symbols within Physics Expressions Using Contour-Based Bounding Box (CBBS) Segmentation Technique

Guessability of Indian picture symbols for communication (IPSC) and picture communication symbols (PCS) among Malayalam-speaking typical adults

The purpose of this study was to investigate the perceived symbol referent relationship for selected symbols in typical adults for two different symbol sets: Indian Picture Symbols for Communication (IPSC) and Picture Communication Symbols (PCS) to identify cultural influences on symbol recognition. A total of 240 typical adults, including 120 nonprofessionals, and 120 health professionals, from Kerala, a southern state in India, participated in the study. A guessability task involving IPSC and PCS symbols for 30 target referents was utilized. Guessability scores for each participant as well as each symbol stimuli across two symbol sets were determined. The guessability scores for IPSC were significantly (p <.001) higher than PCS. For both symbol sets, nouns were the most accurately guessed, followed by verbs, adjectives, and prepositions. The results also revealed that prompting and previous exposure to symbols tend to influence the transparency of symbols. Error analyses revealed that visual and conceptual cues within a symbol tend to influence guessability. The results indicate that cultural and linguistic factors play a role in symbol guessability. The study highlights the importance of investigating the iconicity of IPSC and PCS symbols across different populations within India, before using symbols for educational/clinical purposes.

A review of deep learning methods for digitisation of complex documents and engineering diagrams

This paper presents a review of deep learning on engineering drawings and diagrams. These are typically complex diagrams, that contain a large number of different shapes, such as text annotations, symbols, and connectivity information (largely lines). Digitising these diagrams essentially means the automatic recognition of all these shapes. Initial digitisation methods were based on traditional approaches, which proved to be challenging as these methods rely heavily on hand-crafted features and heuristics. In the past five years, however, there has been a significant increase in the number of deep learning-based methods proposed for engineering diagram digitalisation. We present a comprehensive and critical evaluation of existing literature that has used deep learning-based methods to automatically process and analyse engineering drawings. Key aspects of the digitisation process such as symbol recognition, text extraction, and connectivity information detection, are presented and thoroughly discussed. The review is presented in the context of a wide range of applications across different industry sectors, such as Oil and Gas, Architectural, Mechanical sectors, amongst others. The paper also outlines several key challenges, namely the lack of datasets, data annotation, evaluation and class imbalance. Finally, the latest development in digitalising engineering drawings are summarised, conclusions are drawn, and future interesting research directions to accelerate research and development in this area are outlined.

A comprehensive end-to-end computer vision framework for restoration and recognition of low-quality engineering drawings

The digitization of engineering drawings is crucial for efficient reuse, distribution, and archiving. Existing computer vision approaches for digitizing engineering drawings typically assume the input drawings have high quality. However, in reality, engineering drawings are often blurred and distorted due to improper scanning, storage, and transmission, which may jeopardize the effectiveness of existing approaches. This paper focuses on restoring and recognizing low-quality engineering drawings, where an end-to-end framework is proposed to improve the quality of the drawings and identify the graphical symbols on them. The framework uses K-means clustering to classify different engineering drawing patches into simple and complex texture patches based on their gray level co-occurrence matrix statistics. Computer vision operations and a modified Enhanced Super-Resolution Generative Adversarial Network (ESRGAN) model are then used to improve the quality of the two types of patches, respectively. A modified Faster Region-based Convolutional Neural Network (Faster R-CNN) model is used to recognize the quality-enhanced graphical symbols. Additionally, a multi-stage task-driven collaborative learning strategy is proposed to train the modified ESRGAN and Faster R-CNN models to improve the resolution of engineering drawings in the direction that facilitates graphical symbol recognition, rather than human visual perception. A synthetic data generation method is also proposed to construct quality-degraded samples for training the framework. Experiments on real-world electrical diagrams show that the proposed framework achieves an accuracy of 98.98% and a recall of 99.33%, demonstrating its superiority over previous approaches. Moreover, the framework is integrated into a widely-used power system software application to showcase its practicality. The reference codes and data can be found at https://github.com/Lattle-y/AI-recognition-for-lq-ed.git Future work will focus on improving the generalizability of the proposed framework to different quality degradation scenarios and extrapolating the application to different engineering domains.

Application of Regional Symbol Recognition and Collaborative Design Based on Deep Learning in Cultural Heritage

Application of Regional Symbol Recognition and Collaborative Design Based on Deep Learning in Cultural Heritage

Project-Based Learning Integrated with STEAM: A Study on Educational Pop-Up Books for Early Literacy

This study evaluates the effectiveness of integrating Project-Based Learning (PjBL) with Science, Technology, Engineering, Arts, and Mathematics (STEAM) to enhance literacy skills among children aged 5-6. Employing a quasi-experimental design, 30 TK Cornerstone Homestyle Education students were selected and divided into experimental and control groups. The experimental group engaged in PjBL integrated with STEAM, while the control group followed conventional methods. Pre-tests and post-tests were administered to assess literacy skills, focusing on reading habits, symbol recognition, word writing, and constructing written pieces. Data were collected through tests and observation sheets and analyzed using descriptive and inferential statistics via IBM SPSS Statistics version 21. Results showed significant literacy skill improvements in the experimental group compared to the control group, with higher post-test scores and increased engagement. Instrument validity was confirmed through item analysis, and reliability was ensured with a Cronbach's Alpha of 0.74. Observations revealed high implementation quality in both groups, but the experimental group demonstrated a more substantial increase in literacy levels. This study concludes that STEAM-integrated PjBL effectively enhances early literacy, promotes creativity, and engages students actively in learning. The findings imply the need for broader application of this method in early childhood education and suggest further research to explore long-term impacts and applicability across diverse educational contexts. Despite limitations such as sample scope and short-term intervention, this research supports adopting interdisciplinary approaches for improved educational outcomes.

Improving Handwritten Mathematical Expression Recognition via Similar Symbol Distinguishing

Handwritten mathematical expression recognition (HMER) is an essential task in the OCR community, which consists of two sub-tasks, i.e., symbol recognition and structure parsing. Modern literature treats HMER as a LaTeX sequence predicting problem that simultaneously recognizes symbols and parses the structures of MEs. Although deep learning-based HMER methods have been achieving promising results on public benchmarks, it is admitted that the misclassification error between visually similar symbols still prevents these approaches from more generalized scenes. In this paper, we try to solve this issue from three aspects. 1) We enhanced the feature extraction progress by introducing path signature features, which incorporates local writing details and global spatial information. 2) We developed a language model that uses contextual information to correct the symbols misclassified by vision-only-based recognition models. 3) We solved the misalignment problem in existing ensemble method by designing a dynamic time warping (DTW) based algorithm. By combining the above improvements, our method achieved state-of-the-art results on three CROHME benchmarks, outperforming previous methods by a large margin.

ИНТЕЛЛЕКТУАЛЬНАЯ БЕСПРОВОДНАЯ СЕНСОРНАЯ СЕТЬ С ФУНКЦИЕЙ ПОТОКОВОГО РАСПОЗНАВАНИЯ МНОГОЧАСТОТНЫХ СИМВОЛОВ

Intelligent wireless sensor networks are an innovative class of technologies that combine wireless communications and sensor information systems to create dynamic and flexible data collection and analysis systems. The article proposes a variant of the method for stream recognition of multi-frequency symbols generated by a group of information sources with the possibility of significantly improving the energy and information indicators of the data transmission channel.

Developing Topographic Map Study Skills in Advanced-Level Geography Students: A Teacher’s Experiences

Map work is a core component of the geography curriculum, but it presents unique challenges for both students and teachers. Students must have a high level of cognitive and conceptual development to read and interpret a map. Teachers, too, often find it difficult to instill the necessary skills for graphic literacy. The unique challenges associated with topographic map study skills are highly relevant to the choice of this subject. The primary goal of this study was to help advanced-level geography students improve their topographic map study skills. For this study, the action research method was used as a research method. Following the pre-test, four students with lower grades were chosen as a sample. Thematic analysis is performed on the data. This research found that most of the students in year 12 felt that they had some issues with incorrect topography identification based on map observation, incorrect recognition of standard symbols from map observation, incorrectly calculating the area of a map, difficulties comprehending the relationship between physical and cultural landscapes, and difficulties with reading and analysing a map. The research then revealed that students require fundamental knowledge of drawing, reading, and interpreting maps. It is also critical to teach map work in as practical a manner as possible. Teachers can use models as teaching aids and the group discussion method as a teaching method to help students develop these skills. Teachers’ peer intervention, individual attention, and discussion with friends all help to increase knowledge of basic topographic map concepts. It contends that the sophistication and complexity of the skills required to interpret topographical maps should not be underestimated. Teachers must be made aware of how students acquire map reading skills and the difficulties they face during this process so that teaching programmes that correspond to students’ levels of cognitive development can be developed. The study’s findings and recommendations have implications for geography teachers, textbook authors, and educational authorities, particularly those involved in curriculum and syllabus development.

Application of integrated image processing technology based on PCNN in online music symbol recognition training

Application of integrated image processing technology based on PCNN in online music symbol recognition training

A Short Review for Handwritten Math Expression Recognition Techniques

Handwritten Math Expression recognition is an active area of research that aims to enable machines to automatically interpret handwritten mathematical notation. This technology has many potential applications in education, office automation, and assisting people with visual impairments. In this review, we provide a comprehensive overview of the current state-of-the-art in HME recognition. Specifically, we summarize key preprocessing techniques, feature extraction methods, classification models, benchmark datasets, and performance metrics that have been explored over the past decade. Preprocessing techniques covered include binarization, normalization, smoothing, and outlier removal. Both handcrafted features like gradients and angles as well as automatically learned features from neural networks are discussed. We review the use of Hidden Markov Models, Support Vector Machines, Convolutional Neural Networks, Recurrent Neural Networks like LSTM, and more recently Transformer models for this task. Key benchmark datasets like CROHME 2014 and 2016 are analyzed. Performance metrics like symbol recognition rates, expression recognition rates, and expression structure prediction are compared across different techniques. We highlight strengths and limitations of the reviewed approaches. Finally, we outline important open challenges and promising directions for advancing HME recognition, such as larger datasets, multi-modal learning, and incorporation of syntactic and semantic context. This comprehensive review will serve as a valuable reference for researchers and developers working on interpreting handwritten mathematical expressions.

Application of integrated image processing technology based on PCNN in online music symbol recognition training

Application of integrated image processing technology based on PCNN in online music symbol recognition training

Orthogonal spatial binary coding method for high-speed 3D measurement.

Temporal phase unwrapping based on single auxiliary binary coded pattern has been proven to be effective for high-speed 3D measurement. However, in traditional spatial binary coding, it often leads to an imbalance between the number of periodic divisions and codewords. To meet this challenge, a large codewords orthogonal spatial binary coding method is proposed in this paper. By expanding spatial multiplexing from 1D to 2D orthogonal direction, it goes beyond the traditional 8 codewords to 27 codewords at three-level periodic division. In addition, a novel full-period connected domain segmentation technique based on local localization is proposed to avoid the time-consuming global iterative erosion and complex anomaly detection in traditional methods. For the decoding process, a purely spatial codewords recognition and a spatial-temporal hybrid codewords recognition methods are established to better suppress the percentage offset caused by static defocusing and dynamic motion, respectively. Obviating the need for intricate symbol recognition, the decoding process in our proposed method encompasses a straightforward analysis of statistical distribution. Building upon the development of special spatial binary coding, we have achieved a well-balance between low periodic division and large codewords for the first time. The experimental results verify the feasibility and validity of our proposed whole image processing method in both static and dynamic measurements.

Understanding Map Misinterpretation: Factors Influencing Correct Map Reading and Common Errors

Misinterpreting maps can have serious consequences, especially in situations requiring quick decisions like using car navigation systems. Studies indicate that a map reader’s experience is crucial for understanding maps, but factors such as age, education, and gender can also influence interpretation. However, understanding only the proportion of correctly interpreted information is not enough. It is essential to investigate the types of mistakes made and their causes. To address this, we conducted a study available in six languages with 511 participants who completed an online questionnaire testing their map reading skills. The questions focused on scale usage, mental rotation, and recognizing map categories (relief, line and point symbols, and geographic names). Gender had significant relation with one skill, qualification with two and age with three. Experience was associated to the highest number of skills, a total of four, confirming previous findings. When making mistakes, participants tended to overestimate distances and struggled with conceptual similarities in symbol recognition. Experienced readers often misplaced reference locations of geographic names. The results of the research could be used in the design of large-scale maps (e.g., car navigation), as they allow to reduce typical map reading errors by careful selection of symbol types and placements.

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

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

Pengaruh Penggunaan Media Ular Tangga terhadap Kemampuan Mengenal Lambang Bilangan Anak Usia 5-6

Based on the results of the initial observations that the author made at the Mandiri ABCD Kindergarten in Sipoholon District, it shows that the Kindergarten still does not use various interesting media to facilitate learning in the classroom. This research is motivated by problems that arise in class, namely children are less able to recognize number symbols properly because the child's cognitive abilities have not yet emerged, so that the facilities at school to recognize numbers are minimal, as well as the recognition of number symbols is less attractive. The purpose of this study was to determine the effect of using snakes and ladders media on the ability to recognize number symbols for children aged 5-6 years at Mandiri ABCD Kindergarten, Sipoholon District. The method used in this research is descriptive quantitative research method. The population is all children aged 5-6 years in Mandiri ABCD Kindergarten, Sipoholon District, totaling 108 people and a sample of 20 people is determined using a non-probability sampling technique, namely purposive sampling. Data was collected using a closed questionnaire consisting of 23 items. The results of the data analysis showed that there was a positive and significant influence on the use of snakes and ladders media on the ability to recognize number symbols for children aged 5-6 years at Mandiri ABCD Kindergarten, Sipoholon District. Thus Ha is accepted and H0 is reject.