Personal Handwriting Research Articles

Versatile hybrid transparent triboelectric nanogenerator-solar cell device enables efficient energy harvesting and personal handwriting recognition

The continuous energy supply for wearable electronic devices, including health monitoring sensors and human-machine interface devices, poses a significant challenge to their development. Renewable energy sources, such as nanogenerators and solar cells, offer promising solutions to this challenge. In this study, we explore the potential of a versatile device based on a smart hybrid triboelectric nanogenerator (SH TENG) and photovoltaic (PV) cell for efficient energy harvesting and personal handwriting recognition. A transparent, self-cleaning, UV-protective, bidirectional, non-rigid, lightweight, ultra-durable, eco-friendly, and uniform composite of epoxy resin/ZnO/Ag nanowires-based sandwich-like TENG can produce a power density of 2.3 W m−2. Integrating SH TENG with PV led to improved energy harvesting and increased the charging voltage of the capacitor by up to 5 times. Moreover, this material is a multifunctional sensor capable of detecting temperature, humidity, pressure, handwriting content, and the writer. These features make it an intriguing candidate for e-skin applications. By employing a generalized deep neural network (DNN) model, our device can accurately recognize handwritten letters, numbers, and personal identification with a high level of precision, achieving an accuracy of 97 %. This device can function as an intelligent touch screen with dual-purpose energy production and detection, paving the way for developing highly efficient and sustainable wearable electronic devices.

Improving handwritten digit recognition using hybrid feature selection algorithm

PurposeThe amount of features in handwritten digit data is often very large due to the different aspects in personal handwriting, leading to high-dimensional data. Therefore, the employment of a feature selection algorithm becomes crucial for successful classification modeling, because the inclusion of irrelevant or redundant features can mislead the modeling algorithms, resulting in overfitting and decrease in efficiency.Design/methodology/approachThe minimum redundancy and maximum relevance (mRMR) and the recursive feature elimination (RFE) are two frequently used feature selection algorithms. While mRMR is capable of identifying a subset of features that are highly relevant to the targeted classification variable, mRMR still carries the weakness of capturing redundant features along with the algorithm. On the other hand, RFE is flawed by the fact that those features selected by RFE are not ranked by importance, albeit RFE can effectively eliminate the less important features and exclude redundant features.FindingsThe hybrid method was exemplified in a binary classification between digits “4” and “9” and between digits “6” and “8” from a multiple features dataset. The result showed that the hybrid mRMR + support vector machine recursive feature elimination (SVMRFE) is better than both the sole support vector machine (SVM) and mRMR.Originality/valueIn view of the respective strength and deficiency mRMR and RFE, this study combined both these methods and used an SVM as the underlying classifier anticipating the mRMR to make an excellent complement to the SVMRFE.

Deep learning-enabled real-time personal handwriting electronic skin with dynamic thermoregulating ability

The rapid rise of the Internet of things (IoT) have brought the progress of electronic skin (e-skin). E-skin is used to imitate or even surpass the functions of human skin. Thermoregulating is one of the crucial functions of human skin, it is significant to develop a universal way to realize e-skin thermoregulating. Here, inspired by the sweat gland structure in human skin, we report a simple method for achieving dynamic thermoregulating, attributing to the temperature of microencapsulated paraffin remains unchanged when phase change occurs. Combining with the principle of triboelectric nanogenerator, a deep learning model is employed to recognize the output signals of handwriting different letters on ME-skin, and the recognition accuracy reaches 98.13%. Finally, real-time recognition and display of handwritings are successfully implemented by the ME-skin, which provides a general solution for thermoregulating e-skin and application direction for e-skin in the field of IoT.

Finding an Iconographer’s Handwriting: an Unpublished Icon “St. Minas and Selected Saints” by Nikola Vasilev From Shumen

The work of the iconographer Nikola Vasilev from Shumen is an interesting research topic because of the unique artistic style, longevity and productivity of the artist, as well as because of the wide geographical area of his artistic activity. The investigation of one of his newly discovered icons revealed an additional and extremely curious detail, which complements his manner as an artist and reinforces the perceptions of his personality – his personal handwriting. Present paper aims to express and substantiate the assumption that Vasilev had a habit of inscribing the backs of the icons he painted, taking notes on them. It is assumed that an inscription on the back of an icon “St. Minas with selected saints” signed by Nikola Vasilev displays his personal handwriting.

Multilanguage-handwriting self-powered recognition based on triboelectric nanogenerator enabled machine learning

Handwriting signature is widely used and the main challenge for handwriting recognition is how to obtain comprehensive handwriting information. Triboelectric nanogenerator is sensitive to external triggering force and can be used to record personal handwriting signals and associated characteristics. In this work, micro/nano structure textured TENG acting as a smart self-powered handwriting pad is developed and its effectiveness for handwriting recognition is demonstrated. Three individuals' handwriting signals of English words, Chinese characters and Arabic numerals are acquired by leaf-inspired TENG, and the other three people's handwriting signals of English sentences and the corresponding Chinese sentences are obtained by cylindrical microstructured PDMS based TENG, and these signals exhibit unique features. Combined with the machine learning method, the people's handwriting was successfully identified. The classification accuracies of 99.66%, 93.63%, 91.36%, 99.05%, and 97.73% were reached for English words, Arabic numerals, Chinese characters, English sentences, and the corresponding Chinese sentences, respectively. The results strongly suggested that the textured TENG exhibited great potential in personal handwriting signature identification, security defense, and private information protection applications. This work presented a killer approach for multilanguage handwriting signal sensing and recording. We reported a smart self-powered handwriting pad based on micro/nano-structures textured TENG for sensing different individuals’ handwriting. The obtained signals exhibited unique features both in time domain and frequency domain which could be used in personal handwriting signature identification. For the first time, a novel solution for recognizing personal handwriting combing TENG based smart self-powered device, advanced signal processing and machine learning method was reported. We successfully demonstrated that extremely high classification accuracies achieved by using the proposed advanced technology. • TENG based self-powered handwriting pad was designed and fabricated. • The handwriting pad was sensitive and rapidly-responding to handwriting behavior. • Handwriting was recognized by combing the handwriting pad and machine learning method. • Extremely high classification accuracies were obtained for three kinds of characters.

Neural substrates underlying progressive micrographia in Parkinson's disease.

IntroductionThe neural substrates associated with the development of micrographia remain unknown. We aimed to elucidate the neural substrates underlying micrographia in Parkinson's disease (PD) patients.MethodsForty PD patients and 20 healthy controls underwent handwriting tests that involved free writing and copying. We measured the size of each letter and the resting cerebral glucose metabolic rate of the PD patients and another group of age‐ and sex‐matched 14 healthy controls (HCs), who had not participated in the writing tests, using resting‐state 18F‐fluorodeoxyglucose positron emission tomography.ResultsIn the PD patients, the prevalence of consistent micrographia (CM) associated with free writing was 2.5% for both tasks. Alternatively, the prevalence of progressive micrographia (PM) was 15% for free writing and 17.5% for copying. In the PD patients, there was no significant difference in the letter sizes between these tasks, whereas the variability of the letter sizes for copying was significantly different from that for free writing. The means and decrements in letter sizes in either task were not significantly correlated with the severity of brady/hypokinesia in the PD patients. For free writing, the PD patients with PM showed glucose hypometabolism in the anterior part of the right middle cingulate cortex, including the rostral cingulate motor area, compared with those without PM. For copying, the PD patients with PM showed glucose hypometabolism in the right superior occipital gyrus, including V3A, compared with those without PM.ConclusionsThese findings suggest that PM in free writing in PD patients is caused by the difficulty of monitoring whether the actual handwriting movements are desirable for maintaining letter size during self‐paced handwriting. By contrast, PM in copying in PD patients is evoked by a lack of visual information about the personal handwriting and hand motions that are used as cues for maintaining letter sizes.

Emotions identification utilizing periodic handwriting on mobile surfaces

The purpose of this study is to between the learners’ emotional characteristics and styles in touch screen environments. We propose a method to identify the variety of learners' boredom in the learning process utilising handwriting data. The novelty of the method is to avoid explicit polling of learners how do they feel. We use the recurring acquiring of personal handwriting data utilising the computational power of both a mobile device and cloud-based resources. Also, we use machine learning-based sentiment detection in the research. We smoothly inject periodic handwriting tests convolving them with learning objects to study the correlation between learners’ emotions dynamic, they demonstrate, and the ability to focus and think critically. With the help of machine-learning methods and new communication protocols, we can step up the student-centric mobile-based education process by taking advantage of the latest achievements in a big data analysis and cloud computing. Also, we clarify the conceptual model for the testbed used in the experiment. The findings may likely impact the future personalized e-learning systems.

EasyFont

Generating personal handwriting fonts with large amounts of characters is a boring and time-consuming task. For example, the official standard GB18030-2000 for commercial font products consists of 27,533 Chinese characters. Consistently and correctly writing out such huge amounts of characters is usually an impossible mission for ordinary people. To solve this problem, we propose a system, EasyFont , to automatically synthesize personal handwriting for all (e.g., Chinese) characters in the font library by learning style from a small number (as few as 1%) of carefully-selected samples written by an ordinary person. Major technical contributions of our system are twofold. First, we design an effective stroke extraction algorithm that constructs best-suited reference data from a trained font skeleton manifold and then establishes correspondence between target and reference characters via a non-rigid point set registration approach. Second, we develop a set of novel techniques to learn and recover users’ overall handwriting styles and detailed handwriting behaviors. Experiments including Turing tests with 97 participants demonstrate that the proposed system generates high-quality synthesis results, which are indistinguishable from original handwritings. Using our system, for the first time, the practical handwriting font library in a user’s personal style with arbitrarily large numbers of Chinese characters can be generated automatically. It can also be observed from our experiments that recently-popularized deep learning based end-to-end methods are not able to properly handle this task, which implies the necessity of expert knowledge and handcrafted rules for many applications.

Letters from non-professional writers in sixteenth-century France and their linguistic importance

The non-conventional spellings found in letters written in French before the 19th century by people whose business was not writing tend to be summarily dismissed as fautes d’orthographe, attributable to the ignorance and even lack of intelligence of the writer. Such attitudes have led to the discarding of potentially valuable material for investigating language variation in the past and for deepening our understanding of the multi-facetted process of sound change. Happily, linguists concerned with variation and change are now overthrowing this prejudice and have begun assembling corpora of such letters from the 17th and 18th centuries. Few texts of this type survive from earlier periods, but we shall see here that some are to be found in the personal letters sent to Marie de Guise, when she was queen and queen-regent in Scotland (1538–1560). In this essay we will look at one of them in detail, focusing on the non-conventional spellings we find there, to discover what they might tell us (a) about the writer’s spoken language and (b) about her approach to vernacular spelling. It looks as though the writer deliberately elaborated her own eclectic but highly coherent spelling system, through which she sought to express her individual social identity, in the same way as people seem always to have done with their personal hand-writing.

A Stroke Shape and Structure Based Approach for Off-line Chinese Handwriting Identification

Handwriting identification is a technique of automatic person identification based on the personal handwriting. It is a hot research topic in the field of pattern recognition due to its indispensible role in the biometric individual identification. Although many approaches have emerged, recent research has shown that off-line Chinese handwriting identification remains a challenge problem. In this paper, we propose a novel method for off-line Chinese handwriting identification based on stroke shapes and structures. To extract the features embedded in Chinese handwriting characters, two special structures have been explored according to the trait of Chinese handwriting characters. These two structures are the bounding rectangle and the TBLR quadrilateral. Sixteen features are extracted from the two structures, which are used to compute the unadjusted similarity, and the other four commonly used features are also computed to adjust the similarity adaptively. The final identification is performed on the similarity. Experimental results on the SYSU and HanjaDB1 databases have validated the effectiveness of the proposed method.

Automatic Generation of Chinese Calligraphic Writings with Style Imitation

An automatic algorithm can generate Chinese calligraphy by quantitatively representing the characteristics of personal handwriting acquired from learning examples.

Combining shape and physical modelsfor online cursive handwriting synthesis

This paper proposes a novel learning-based approach to synthesizing cursive handwriting of a user's personal handwriting style by combining shape and physical models. In the training process, some sample paragraphs written by a user are collected and these cursive handwriting samples are segmented into individual characters by using a two-level writer-independent segmentation algorithm. Samples for each letter are then aligned and trained using shape models. In the synthesis process, a delta log-normal model based conditional sampling algorithm is proposed to produce smooth and natural cursive handwriting of the user's style from models.

Improvement of numeral recognition using personal handwriting characteristics based on clustering

AbstractCorrectly recognizing characters with peculiarities for each writer is a difficult problem. The process of absorbing variations in individual writing by creating an individual dictionary is also difficult when a writer is not specified and the total number of writers is large. In this paper the authors propose a method to improve the results of isolated character recognition in forms in which the same writer writes many characters by taking the characteristics of the writer's writing on a form as a character distribution in a character feature space. In concrete terms, the authors first perform isolated character recognition on all characters on the same form. Then, based on the results of isolated character recognition, clustering of input character groups is performed for each character category. Clusters which are very likely to include misrecognized characters from isolated character recognition are extracted based on the results of clustering. Then character categories in the extracted cluster are automatically amended based on the distance from all clusters in other categories. In the same fashion, automatic amending is performed for rejected characters. Based on experiments to evaluate handwritten numerals on OCR forms, the authors show that the precision of numeral recognition is improved by using this approach as a form of postprocessing for isolated character recognition. © 2002 Wiley Periodicals, Inc. Syst Comp Jpn, 33(7): 104–113, 2002; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/scj.1146

Recognition of handwritten similar Chinese characters by self-growing probabilistic decision-based neural network.

Recognition of similar (confusion) characters is a difficult problem in optical character recognition (OCR). In this paper, we introduce a neural network solution that is capable of modeling minor differences among similar characters, and is robust to various personal handwriting styles. The Self-growing Probabilistic Decision-based Neural Network (SPDNN) is a probabilistic type neural network, which adopts a hierarchical network structure with nonlinear basis functions and a competitive credit-assignment scheme. Based on the SPDNN model, we have constructed a three-stage recognition system. First, a coarse classifier determines a character to be input to one of the pre-defined subclasses partitioned from a large character set, such as Chinese mixed with alphanumerics. Then a character recognizer determines the input image which best matches the reference character in the subclass. Lastly, the third module is a similar character recognizer, which can further enhance the recognition accuracy among similar or confusing characters. The prototype system has demonstrated a successful application of SPDNN to similar handwritten Chinese recognition for the public database CCL/HCCR1 (5401 characters x200 samples). Regarding performance, experiments on the CCL/HCCR1 database produced 90.12% recognition accuracy with no rejection, and 94.11% accuracy with 6.7% rejection, respectively. This recognition accuracy represents about 4% improvement on the previously announced performance. As to processing speed, processing before recognition (including image preprocessing, segmentation, and feature extraction) requires about one second for an A4 size character image, and recognition consumes approximately 0.27 second per character on a Pentium-100 based personal computer, without use of any hardware accelerator or co-processor.

Verification of personal handwriting characteristics for numerals and its application to recognition

Chracters written by the same writer are expected to have two characteristics. Characters belonging to the same category have similar shapes and characters belonging to different categories are correlated in shape to some extent. In this paper, these characteristics are quantitatively verified through shape quantification and are successfully applied to detect misrecognized patterns, difficult to detect by pattern information only.

Importance of skin temperature in the regulation of sweating.

Human sweating regulation at rest, evaluating thermal inputs effects on thermoregulatory center and internal hypothalamic and skin temperatures