Symbol Recognition Research Articles

I.A. Bunin and F.M. Dostoevsky: Some Reflections on Poetics

Ivan Bunin’s works have long been considered in the broad context of Russian and world literature. An original modern author, he inherited traditions and created new models in poetics. Among the writers whose heritage Bunin refers to, Fyodor Dostoevsky seems most alien and divergent to him as a result of the striking incompatibility of their literary languages. An outstanding master of style, Bunin contradicts Dostoevsky’s novels with their stream-of-consciousness, mental candor, searching for God and truth, and, let us be honest, with all their evident neglect of the aesthetic part of the text. Bunin also exposes a deep abyss in a human soul, but his fine style is a real proof for the recognition of new symbols and philosophy. Closer penetration into the texts of Bunin leads to almost unexpected discoveries. The Petersburg image of Dostoevsky inter alia affects the “Paris text” of Bunin. Already in his pre-revolutionary works the village as locus amoenus (in the broadest sense as nature or manor) opposes the locus horribilis of the metropolis in “Dostoyevsky style,” with all its civilizational gains and losses ( Looped Ears ). Bunin brings many strokes outlined by his predecessor to its logical conclusion, first of all Godlessness, a total abandonment of a human soul in a megalopolis. Being organically included in Bunin’s literary work, Dostoevsky is his direct predecessor in the verbalization of urban landscapes ( Un petit accident ). Bunin turns toward Dostoevsky and if not consciously then typologically relies on his traditions. The most elusive side of Bunin’s nature, the thinker, becomes evident due to a small comparative analysis of two strikingly dissimilar poetics.

Offline music symbol recognition using Daisy feature and quantum Grey wolf optimization based feature selection

Handwritten music symbol recognition is considered by the research fraternity as a critical research problem. It becomes more critical when the symbols are collected from handwritten music sheets in offline mode. Most of the research findings, available in the literature, have tried to recognize the said symbols using various shape based features. But this approach limits system performance when we dealt with lookalike symbols such as half note, eight note and quarter note. To encounter this, in the present work we have used a texture based feature descriptor, called Daisy, for the said purpose. Though Daisy descriptor yields reasonably good recognition accuracy, but it generates a high dimensional feature vector. Hence, in this work, Quantum concept inspired Grey Wolf Optimization, named as QGWO, has been applied to select optimal feature subset from this high dimensional feature vector. We have applied the proposed method on six different standard music symbol datasets that include HOMUS, Capitan_score_uniform, Capitan_score_non-uniform, Fornes, Rebelo_real and Rebelo_synthetic datasets. On these datasets we have achieved recognition accuracies 93.07%, 99.22%, 99.20%, 99.49% and 100.00% respectively with 39.63%, 49.75%, 42.50%, 67.62%, 54.37% and 71.25% of actual feature dimension (i.e., 800) respectively. Additionally, we have compared our results with some state-of-the-art methods along with two recent deep learning based models, and it has been found that the present approach outperforms those.

Constraining Stroke Order During Manual Symbol Learning Hinders Subsequent Recognition in Children Under 4 1/2 Years.

In the age of technology, writing by hand has become less common than texting and keyboarding. Learning letters by hand, however, has been shown to have profound developmental importance. One aspect of writing by hand that has been understudied is the effect of learning symbols stroke-by-stroke, a dynamic action that does not occur with keyboarding. We trained children to draw novel symbols in either an instructed stroke order or in a self-directed stroke order and tested: (1) whether learning novel symbols in a self-directed stroke order benefits subsequent recognition more than learning in a specified stroke order, (2) whether seeing novel symbols unfold in the stroke order that was taught would aid in recognition, and (3) whether any effects are age-dependent. Our results demonstrate that producing a symbol with a self-directed stroke order provides more benefit to symbol recognition than instructed stroke orders in 4.0–4.5-year-old children but not in 4.5–5.0-year-old children. We found, further, that the observed recognition benefits were not affected by seeing the symbol unfold in the same stroke order it was learned during testing, suggesting that the learning was not reliant upon the exact stroke order experienced during learning. These results stress the importance of allowing children to produce symbols in a self-directed manner and, by extension, that constraining how a child learns to write can adversely affect subsequent recognition.

Development of the Principal Symbol Recognition Method (Letters, Digital) for the Personal Computer Program

Development of the Principal Symbol Recognition Method (Letters, Digital) for the Personal Computer Program

Learning activities using worksheet characterized by the recognition of mathematical symbols

One of the purposes of learning mathematics in college is to improve the ability of critical thinking and problem-solving. Before solving the problems, the college students need to recognize the problems not excepted the mathematics symbols written in the problem. Thereover it is important for the problem solver to aware and recognizes the meaning of mathematics symbols, called recognition of mathematical symbols. This educational design research aims to describe the development of learning activities using a worksheet to recognize the mathematical symbol. The design research phase consists of four successive phases: knowledge, designing, experimenting and analyzing. Findings reveal that: College students can distinguish between the form of functions and the value of functions; College students transform to fy (x, y) when solving problems; College students can read symbol but need more time to interpret that symbol rather than fxx (x, y) symbol. At the end of the learning practice, college students that doing error to recognize mathematics symbols are less than at the first teaching practice. The college students can recognize mathematical symbols well and then solve the problem correctly using correct mathematics symbols.

The Computer Vision-based Tolerancing Callout Detection Model

Abstract Tolerancing symbols play an important role in mechanical product drawings, and they directly determine the functions, mating properties, interchangeability and working life of geometrical products. A symbolic tolerancing callout containing a set of symbols represents a set of pre-ordered operations with attributes. It includes an amount of knowledge from the drawing and standard documents, which is often reconstructed manually by engineers. Thus, at the same time, a symbolic tolerancing callout makes it difficult for the end-user to understand and interpret these callouts manually. To this end, this study puts forward a tolerancing callout detection model via the use of off-the-shelf costumer-grade cameras on current mobile devices for extracting and recognizing tolerancing callout blocks and symbols in them intelligently. This model has four core components: image preprocessing, callout location and extraction, symbol and character segmentation, and deep learning-based symbol recognition. The image preprocessing component is developed to remove the interferences on the target technical drawings through the corresponding morphological methods. This study proposes a novel solution on callout block locations and extractions in callout intensive scenarios since the callout locations and extractions can directly affect the accuracy of symbol and character recognitions. Then, Huff Transform and improved projection methods have been devised to symbol and character segmentations. Finally, this study constructed a convolutional neural network (CNN) to train a symbol recognition model. The experimental results show that the proposed model gains applicability on intelligent callout extractions and the corresponding symbol recognitions.

Multi-Feature Learning by Joint Training for Handwritten Formula Symbol Recognition

Given the similarity of handwritten formula symbols and various handwriting styles, this paper proposes a squeeze-extracted multi-feature convolution neural network (SE-MCNN) to improve the recognition rate of handwritten formula symbols. The system proposed in this paper integrates the eight-directional feature of the original sequence in the convolutional layer, which significantly compensates for the lost dynamic trajectory information in the handwritten formula symbol. Meanwhile, the joint loss is constructed to improve the discriminability of features in the way of supervised learning, which enlarges the inter-class difference and decreases inner-class similarity. The standard mathematical formula symbol library provided by the Competition Organization on Recognition of Online Handwritten Mathematical Expression (CROHME) is used to verify the effectiveness of the proposed algorithm. Experiments show that the proposed SE-MCNN approach outperforms the state-of-the-art methods even at the condition of without using the data augmentation.

Symbol recognition system based on 3D stereo vision

With the continuous development of computer science and technology, symbol recognition systems may be converted from two-dimensional space to three-dimensional space. Therefore, this article mainly introduces the symbol recognition system based on 3D stereo vision. The three-dimensional image is taken by the visual coordinate measuring machine in two places on the left and right. Perform binocular stereo matching on the edge of the feature points of the two images. A corner detection algorithm combining SUSAN and Harris is used to detect the left and right camera calibration templates. The two-dimensional coordinate points of the object are determined by the image stereo matching module, and the three-dimensional discrete coordinate points of the object space can be obtained according to the transformation relationship between the image coordinates and the actual object coordinates. Then draw the three-dimensional model of the object through the three-dimensional drawing software. Experimental data shows that the logic resources and memory resources occupied by image preprocessing account for 30.4% and 27.4% of the entire system, respectively. The results show that the system can calibrate the internal and external parameters of the camera. In this way, the camera calibration result will be more accurate and the range will be wider. At the same time, it can effectively make up for the shortcomings of traditional modeling techniques to ensure the measurement accuracy of the detection system.

Perception of Civil Identity Symbols in Russia: (Based on Focus Groups)

Introduction. The problem of identity is one of the key in both theoretical and applied scientific research of various directions, including in the framework of political psychology. This is largely due to the importance of the formation of common vectors of development of the state, based on the identity shared by most citizens. In this scientific article, the topic of the formation of state-civil identity by means of symbolic capital is actualized, which in turn can both harmonize social relations and introduce dysfunctionality, and be an instrument for mobilizing or polarizing society. The authors attempt to study the social product of the representation and construction of contemporary reality in Russia. Materials and Methods. As a theoretical and methodological research strategy, systemic, integrated and analytical approaches were made. The materials for the scientific work were the results of applied research, in particular, focus group interviews, which, thanks to synergies, allowed us to obtain diverse information about the subject of analysis and to more deeply present its perception. Participants in group discussions were residents of the island. Saransk and two municipal regions of the Republic of Mordovia. Results. Unique data were obtained, on the basis of which it is possible to draw conclusions about the features of the perception of conceptual structures of the formation of state-civil identity in modern Russian society. The difference between the older generation and young people in the perception and symbolic reflection of Russian reality was noted. Moreover, both the sources of obtaining information turned out to be excellent, as did personal and collective positions in determining their own role in the process of creating and assimilating symbols of identity, the level of recognition of symbols of different historical eras, the stability and rooting of the value system. In terms of the perception of symbolic identity elements uniting all age groups of respondents, several phenomena are thematically highlighted, among them “border trauma”, “we are the opposition”, “separation from the powers that be”, “Russian & imperial & Soviet”, “nationalities of Russia = peoples of the USSR” and etc. Discussion and Conclusions. Understanding the specifics of perception of the symbolic-value system of Russians allows us to analyze and evaluate the processes of nation-building and to study the problems of social consolidation. The authors come to the conclusion that the Russians are deficient in spiritual bonds, civil activism is weak; most citizens feel outside the active community.

Integrating Interactive Clothing and Cyber-Physical Systems: A Humanistic Design Perspective.

This study is aimed at bridging the gap from a transdisciplinary perspective between cyber-physical systems (CPS) architecture in the field of information science and emotional design in the field of humanistic science for interactive fashion innovation. Information related to a familiar feeling in the process of interactive clothing design is used to explain how the transformation could be realized from data. By creating the cyber-physical-clothing systems (CPCS), the architecture model in the hyper world and takes the development process of an interactive parent-child clothing as a case study for analyzing the transformation from the physical signal input to the social symbol recognition output. The experimental results, which from the perspective of clothing art design rather than information discipline, show that interactive parent-child clothing is not only suitable for the rehabilitation of autistic children but also recognized by most parents. The reasonable embedding of sensing technology can greatly enhance the added value of clothing products. This study provides a fruitful practical application reference for designers who are engaged in the field of art and design but not familiar with the relevant information technology. Furthermore, the application principle and the technical process of CPCS for further interactive clothing design is explained.

SKETRACK: Stroke-Based Recognition of Online Hand-Drawn Sketches of Arrow-Connected Diagrams and Digital Logic Circuit Diagrams

Digitalization of handwritten documents has created a greater need for accurate online recognition of hand-drawn sketches. However, the online recognition of hand-drawn diagrams is an enduring challenge in human-computer interaction due to the complexity in extracting and recognizing the visual objects reliably from a continuous stroke stream. This paper focuses on the design and development of a new, efficient stroke-based online hand-drawn sketch recognition scheme named SKETRACK for hand-drawn arrow diagrams and digital logic circuit diagrams. The fundamental parts of this model are text separation, symbol segmentation, feature extraction, classification, and structural analysis. The proposed scheme utilizes the concepts of normalization and segmentation to isolate the text from the sketches. Then, the features are extracted to model different structural variations of the strokes that are categorized into the arrows/lines and the symbols for effective processing. The strokes are clustered using the spectral clustering algorithm based on p-distance and Euclidean distance to compute the similarity between the features and minimize the feature dimensionality by grouping similar features. Then, the symbol recognition is performed using modified support vector machine (MSVM) classifier in which a hybrid kernel function with a lion optimized tuning parameter of SVM is utilized. Structural analysis is performed with lion-based task optimization for recognizing the symbol candidates to form the final diagram representations. This proposed recognition model is suitable for simpler structures such as flowcharts, finite automata, and the logic circuit diagrams. Through the experiments, the performance of the proposed SKETRACK scheme is evaluated on three domains of databases and the results are compared with the state-of-the-art methods to validate its superior efficiency.

A deficiência visual em foco: estratégias lúdicas na Educação Matemática Inclusiva

O objetivo deste artigo é discutir sobre o ensino de Matemática para alunos com deficiência visual, apontando expressões lúdicas enquanto estratégia de ensino no âmbito da inclusão escolar. As expressões lúdicas podem compor-se de jogos, brincadeiras e outras atividades que venham a despertar o espírito lúdico nos sujeitos que as realizam. A partir dos estudos aqui analisados e da identificação de jogos pedagógicos táteis e digitais, acredito que os materiais considerados lúdicos podem contribuir para o desenvolvimento do sistema háptico ou tato ativo, uma vez que, através deste sistema, os indivíduos sem acuidade visual percebem o mundo ao seu redor e podem construir diferentes conceitos matemáticos, potencializando a aprendizagem neste componente curricular. Por este motivo, serão descritos diferentes materiais e jogos que possibilitem tratar conteúdos matemáticos presentes na Educação Básica, especialmente aqueles construídos e testados junto a alunos cegos e com baixa visão. Os resultados apontam para a necessidade de realizar mais pesquisas que apresentem outras alternativas lúdicas, para o desenvolvimento do processo de ensino e aprendizagem de conceitos matemáticos pouco contemplados em tais materiais ou jogos. Em sua maioria, as atividades abordam conceitos de função, geometria, progressão geométrica, as quatro operações básicas, e o reconhecimento dos símbolos que representam os números. Entretanto, há inúmeros outros conteúdos matemáticos que ainda são trabalhados em sala de aula com um forte apelo visual, demandando outras estratégias que favorecem a inclusão e aprendizagem de pessoas com deficiência visual.

Incremental Learning of Hand Symbols Using Event-Based Cameras

Conventional cameras create redundant output especially when the frame rate is high. Dynamic vision sensors (DVSs), on the other hand, generate asynchronous and sparse brightness change events only when an object in the field of view is in motion. Such event-based output can be processed as a 1D time sequence, or it can be converted to 2D frames that resemble conventional camera frames. Frames created, e.g., by accumulating a fixed number of events, can be used as input for conventional deep learning algorithms, thus upgrading existing computer vision pipelines through low-power, low-redundancy sensors. This paper describes a hand symbol recognition system that can quickly be trained to incrementally learn new symbols recorded with an event-based camera, without forgetting previously learned classes. By using the iCaRL incremental learning algorithm, we show that we can learn up to 16 new symbols using only 4000 samples for each symbol and achieving a final symbol accuracy of over 80%. The system achieves latency of under 0.5s and training requires 3 minutes for 5 epochs on an NVIDIA 1080TI GPU.

A Simplified Research for Mathematical Expression Recognition and Its Conversion to Speech

The number of visually impaired people appearing for various examination is increasing every year while on the other hand, there are several blind aspirants who are willing to enrich their knowledge through higher studies. Mathematics is one of the key language (subject) for those who are willing to pursue higher studies in science stream. There is a lot of advanced Braille techniques and OCR to speech conversion software's made available to help visual impaired community to pursue their education but still the number of visually impaired students getting admitted to higher education is less. This is not because most of the data is on paper in the form of books and documents. So, there is a great need to convert information from the physical domain into the digital domain which would help the visually impaired people to read the advanced mathematics text independently. Optical Character Recognition (OCR) systems for mathematics have received considerable attention in recent years due to the tremendous need for the digitization of printed documents. Existing literature reveals that, most of the works concentrated on recognizing handwritten mathematical symbols and some works revolve around complex algorithms. This paper proposes a simple, yet efficient approach to develop an OCR system for mathematics and its conversion to speech. For Mathematical symbol recognition, Skin and Bone algorithm is proposed, which proved its efficiency on a variety of data set. The proposed methodology has been tested on 50 equations comprising various symbols such as integral, differential, square, square root and currently achieving recognition rate of 92%.

Reading as a Visual Act: Recognition of Visual Letter Symbols in the Mind and Brain

A great deal of our time as adults is spent reading: Deriving meaning from visual symbols. Our brains, which may have evolved to recognize a lion, now recognize the written word “LION”. Without recognizing the letters that comprise a word, we cannot access its meaning or its pronunciation: Letter recognition forms the basis of our ability to read. In this symposium, we will highlight work by a growing number of researchers attempting to bridge the gap in research between vision and language by investigating letter recognition processes, from both a behavioral and brain perspective.

Chart Symbol Recognition Based on Computer Natural Language Processing

ABSTRACT Zhang, X., 2018. Chart symbol recognition based on computer natural language processing. In: Liu, Z.L. and Mi, C. (eds.), Advances in Sustainable Port and Ocean Engineering. Journal of Coastal Research, Special Issue No. 83, pp. 724–728. Coconut Creek (Florida), ISSN 0749-0208. The precise identification of chart symbol is of great significance for ocean sailing. The current recognition methods for chart symbol have obvious shortcomings in recognition efficiency and control accuracy. To address this problem, it is necessary to discuss the construction and implementation of the grammatical rule of chart symbol language from two aspects of theory and practice. In this paper, the grammatical rule and the essential features of chart symbol language are discussed. The transformation of computer language service mode of chart symbol is achieved. Firstly, the description of various chart symbols is carried out by the computer natural language, and the recognition and processing of chart pattern informat...

The application of artificial immune system to solve recognition problems

The present paper is devoted to the creation of a model and algorithm of an artificial immune system (AIS). The proposed model and algorithm are designed to solve the problems of single symbols recognition, symbolic regression, managing autonomous systems (robot). The taxonomy of the proposed artificial immune system model and algorithm of research methodology is described in terms of the natural immune system. The adopted concept of B-cells are responsible for producing antibodies, a special class of complex proteins on the surface of B-lymphocytes, capable of binding to certain types of molecules (antigens) is used. The full set of antigenic receptors of all B-cells is a plurality of antibodies that can be produced by the organism. The developed program complex allows to solve all three problems: single symbols recognition, symbolic regression, managing autonomous systems (robot). Accuracy of calculations is compared to that for other methods, i. e. methods of genetic programming. Computing experiments for each considered task are made.

Cultural Differences on the Recognition of Social Word AAC Graphic Symbols between Korean and American Undergraduate Students

Cultural Differences on the Recognition of Social Word AAC Graphic Symbols between Korean and American Undergraduate Students

Traffic symbol recognition modulates bodily actions.

Traffic signals, i.e., iconic symbols conveying traffic rules, generally represent spatial or movement meanings, e.g., “Stop”, “Go”, “Bend warning”, or “No entry”, and we visually perceive these symbols and produce appropriate bodily actions. The traffic signals are clearly thought to assist in producing bodily actions such as going forward or stopping, and the combination of symbolic recognition through visual perception and production of bodily actions could be one example of embodied cognition. However, to what extent our bodily actions are associated with the symbolic representations of commonly used traffic signals remains unknown. Here we experimentally investigated how traffic symbol recognition cognitively affects bodily action patterns, by employing a simple stimulus-response task for traffic sign recognition with a response of either sliding or pushing down on a joystick in a gamepad. We found that when operating the joystick, participants’ slide reaction in response to the “Go” traffic symbol was significantly faster than their push reaction, while their response time to the “Stop” signal showed no differences between sliding and pushing actions. These results suggested that there was a possible association between certain action patterns and traffic symbol recognition, and in particular the “Go” symbol was congruent with a sliding action as a bodily response. Our findings may thus reveal an example of embodied cognition in visual perception of traffic signals.

A Sketch Recognition Algorithm Based on Bayesian Network and Convolution Neural Network

Most of the existing sketch recognition algorithms are used to restrict the user’s drawing habits to achieve the stroke grouping and recognition. In order to solve the problem, a new sketch recognition algorithm based on Bayesian network and convolution neural network (CNN) is proposed. First, the input sketch is processed by Gaussian low-pass filter and a smoother stroke can be obtained. The stroke of continuous input is divided, then the Bayesian network and CNN are performed on stroke recognition respectively. The recognition result of Bayesian network is adopted when the reliability of stroke is larger than the threshold, otherwise recognition result of CNN will be adopted. The experiment result shows that the proposed algorithm is effective in circuit symbol recognition. The recognition rate was achieved 80.34% in the drawing process, and the final recognition rate was achieved 93.48%.