Search

It is important that a company uses the right means to recruit employees with certain personal characteristics as needed. Nowadays, the techniques to respond to psychological tests on people’s characteristics have been widely understood by most job applicants, so that it is difficult to know their true personality. Graphology is a way to identify a person’s characteristics by analyzing the handwriting from the document text made by the applicant. The two types of text document of each applicant are obtained from people of different ages and different writing times. The methods of graphology used in this research for identifying the handwriting are preprocessing and feature extraction. The preprocessing method uses projection integrals, shear transformations, and template matching. While the feature extraction process applies 10 features, they are, margins, line spacing, space between words, size of writing, style, zone, direction of writing, slope of writing, width of writing and shape of the letter. The result of the experiment from five writers shows the accuracy of writing identification equals to 82%, while personality identification equals to 67,4%.

The handwriting is an object that can describe information about the author implicitly. For example, it is able to predict the gender. Recently, the gender prediction based on handwriting becomes an interesting research. Even in 2013, an competition for prediction gender from handwriting has been held by Kaggle. However, the accuracies of current approaches are relatively low. So, in this study, we attempt to implement Fuzzy Rule-Based Classification Systems (FRBCSs) for gender predictions from handwriting. Three stages are conducted to achieve the objective, as follows: defining some features based on Graphology Techniques (e.g., pressure, height, and margin on writing), collecting real datasets, processing on digital images (i.e., image segmentation, projection profiles, and margin calculation, etc.), and implementing FRBCSs. The implemented algorithm based on FRBCSs in this research is Chi's Algorithm, which is a method based on Fuzzy Logic for classification tasks. Moreover, some experiments and analysis, involving 75 respondents consisting of 36 males and 39 females, have been done to validate the proposed model. From the simulations, the classification rate obtained is 76%. Besides improving the accuracy rate, the proposed model can provide an understandable model by utilizing fuzzy rule-based systems. [ABSTRACT FROM AUTHOR]

Despite the abundant existing literature on the psychological aspects of graphology and visual communication, very little research (if any), has been conducted, as to the links of interpreting personal handmade markings on graphic self-branding processes. This research aimed to investigate possible interrelations between fields of handwriting analysis (graphology) and personal branding, underpinning methods and patterns of building graphic personal identities amongst higher education students. Furthermore, it aimed to promote the use of graphology in self-branding processes. This involved secondary sources of information, along with empirical works, totalling 25 semi-structured interviews and the collection of 97 handwritten samples to detect commonalities/differences of handmade markings. Participants included higher education students and instructors from visual communication fields across two cultural contexts: Saudi Arabia and the United Kingdom. The achieved findings were discussed with two professional UK-based graphologists. Given that self-branding is considered complex and time consuming amongst visual communication students, the outcome proposes an online personal brand design platform, innovating current methods of self-related research, yet grounded on current usages of conventional handwriting and providing a visual scope of relevant design applications, considering internal and external influencing factors. [ABSTRACT FROM AUTHOR]

Abstract Handwritten digits recognition is a challenging problem in recent years. Although many deep learning-based classification algorithms are studied for handwritten digits recognition, the recognition accuracy and running time still need to be further improved. In this paper, an adaptive deep Q-learning strategy is proposed to improve accuracy and shorten running time for handwritten digit recognition. The adaptive deep Q-learning strategy combines the feature-extracting capability of deep learning and the decision-making of reinforcement learning to form an adaptive Q-learning deep belief network (Q-ADBN). First, Q-ADBN extracts the features of original images using an adaptive deep auto-encoder (ADAE), and the extracted features are considered as the current states of Q-learning algorithm. Second, Q-ADBN receives Q-function (reward signal) during recognition of the current states, and the final handwritten digits recognition is implemented by maximizing the Q-function using Q-learning algorithm. Finally, experimental results from the well-known MNIST dataset show that the proposed Q-ADBN has a superiority to other similar methods in terms of accuracy and running time. [ABSTRACT FROM AUTHOR]

Chinese language has enormous number of characters and complicated stroke structures. So it is very difficult to efficiently and accurately identify a Chinese writer from his/her handwritings. This paper proposes a novel writer identification method for Chinese characters commonly used in Japan which can be used in peer-to-peer (P2P) systems. As a preliminary task, we have analyzed the shapes of strokes and the types of block division structures in Chinese characters and selected some characters for writer identification. The method consists of two efficient algorithms, i.e. the Hidden-feature analysis and the Block-type model, which respectively utilize intra-stroke and inter-stroke features of handwritings to enhance the writer identification accuracy. The Hidden-feature analysis makes template classes of reference characters with online features of training samples such as pen-pressure, pen-speed, pen-altitude, and pen-azimuth of each stroke. The Block-type model also creates such classes for writer identification based on offline features, i.e. the positional information about blocks of sample characters. The experimental results show that the Hidden-feature analysis requires eight Chinese characters while the Block-type model requires only four characters and four ones to achieve writer identification accuracy over 98%. Additionally, the results also demonstrate that any eight Chinese characters are enough to achieve an identification accuracy over 99.9% when the combination of the two algorithms is applied. [ABSTRACT FROM AUTHOR]

In the nearly 800 pages that comprise the three volumes of his Graphology Poems 1995-2015 (Five Islands P, 2016), John Kinsella demonstrates an exemplary moral anger registering iterations of colonial “omni-speak” as unethical (1: 93). This paper reads Giorgio Agamben’s Homo Sacer (Stanford UP, 1998) by way of apprehending the rhetorical substrata underpinning discourses of Australia as not just determining a sovereign colonial space; in a place where “history is absurdity […] history is overlay” (Graphology Poems 1: 158), Kinsella shows how indigenous and non-colonial others are consistently cast as extra-juridical and merely sub-human. These Graphology Poems not only anathemise and hex historical falsehoods of nation: Kinsella dares sound out the bullshit, and his iconoclastic language games refuse outright to acquiesce to the epistemically violent nullifications of antipodean identity. [ABSTRACT FROM AUTHOR]

Most of existing approaches in keyword spotting are system-oriented, which did not take into consideration the user's needs. However, a user may want to find words, sentences, or texts that match his target image in his mind. The challenge here is how to formulate one's mental image to reach what he is looking for. The key idea is to design and build a model that properly adapts the human reasoning in information searching through an interactive process. We propose a mental model for handwritten keyword spotting based on relevance feedback, feature weighting, and optimization. This model meets simultaneously the user's needs, the system behavior, and the user -- system relationship. In an appropriate feature space, the query is progressively built from user-supplied keywords, old queries, and spotted images. This dynamic process not only converges toward the desired word images, but also helps the hesitant user to clarify progressively what he is looking for. The proposed model was showcased via a user-friendly interface, which we tested including real users on three well-known handwritten datasets; Institute for Communications, Braunschweig University, Germany/École Nationale d'Ingénieurs de Tunis, Tunisia, Institut für informatik und Angewandte Mathematik, and George Washington. The experimental results show that the proposed method provides promising scores with a reasonable number of refinements. [ABSTRACT FROM AUTHOR]

Character recognition is a well-known area because of its wide applications, including text-searchable documents, digital storage and support, and manual work automation. Recognizing characters is challenging, and, on top of that, writer's writing style habits make handwritten character recognition even more challenging. This article addresses a set of features and classifiers that are less complex to implement and give significant recognition rates for Hindi language characters. The proposed work is based on two shape descriptors, such as (1) histogram of oriented gradients and (2) geometric moments. These descriptors, when used as features, reflect properties of characters that minimize intraclass variations and maximize interclass variations. The generated feature set is tested using two supervised classifiers, namely support vector machine (SVM) and multilayer perceptron (MLP). A thorough investigation into various evaluation parameters has been presented. Experimental results show that high recognition results are obtained when both shape descriptors are used in combination with an SVM classifier. This technique is evaluated on four publicly available databases, and it achieves a recognition rate of 96.8% on one of the datasets. A comparative analysis of the proposed method with relevant and recent works of this field proves its superiority. This work introduces a much less complex and promising approach toward isolated handwritten character recognition. © 2018 SPIE and IS&T [DOI: 10.1117/1.JEI.27.5.051216] [ABSTRACT FROM AUTHOR]

Abstract. We present GRAPHJ, a forensic tool for handwriting analysis. The proposed tool has been designed to implement the real forensic protocol adopted by the "Reparto Investigazioni Scientifiche" of Carabinieri, Italy. GRAPHJ allows the examiner to (1) automatically detect text lines and words in the document, (2) search for a specific character and detect its occurrences in the handwritten text, (3) measure different quantities related to the detected elements (e.g., heights and widths of characters), and (4) generate a report containing measurements, statistics, and the values of all parameters used during the analysis. The generation of the report helps to improve the repeatability of the whole process. The experiments performed on a set of handwritten documents show that GRAPHJ allows one to extract quantitative measures comparable to those acquired manually by an expert examiner. We also report a study on the use of the relative position of the superscript dot of the "i" characters as a parameter to infer the identity of the writer. The study has been performed using GRAPHJ and illustrates its value as a forensic tool. [ABSTRACT FROM AUTHOR]

Unlike the conventional feedforward neural network, an emergent learning technique--which we call extreme learning machine (ELM)--provides a generalized performance of neural network with less user intervention and comparatively faster training. We study ELM with five different activation functions, sigmoidal, sine, hard limiter, triangular basis, and radial basis, for handwritten Indic script identification in multiscript documents. To describe scripts, both script dependent and independent features are computed. For validation, a dataset of 3300 handwritten line-level document images (300 samples per script) of 11 official Indic scripts is used. In our study, we observe that the sigmoidal activation function performs the best regardless of the number of scripts used, i.e., script identification cases: biscript, triscript, and multiscript. © 2018 SPIEand IS&T [DOI: 10.1117/1.JEI.27.5 .051214] [ABSTRACT FROM AUTHOR]

The printed Arabic character recognition are faced numerous challenges due to its character body which are changed depending on its position in any sentence (at beginning or in the middle or in the end of the word). This paper portrays recognition strategies. These strategies depend on new pre-processing processes, extraction the structural and numerical features to build databases for printed alphabetical Arabic characters. The database information that obtained from features extracted was applied in recognition stage. Minimum Distance Classifier technique (MDC) was used to classify and train the classes of characters. The procedure of one character against all characters (OAA) was used in determining the rate of recognition. The suggested approaches have yielded unique and encouraging results in terms of accuracy in which the recognition rate reached to 97.28%. These approaches are faster and more efficient than other methods. [ABSTRACT FROM AUTHOR]

Abstract: The premise of this follow‐up sister study to “Measuring the Frequency Occurrence of Handwriting and Handprinting Characteristics” was to collect a representative population sampling of numerals and assess how many participants utilize each of the predetermined characteristics as found in their specimens. A total of 1410 handwriting specimen forms were collected from across the United States and pared to 1025 to obtain a proper representative sample of the U.S. adult population based on the same demographics used in the original 2017 study. This study provides frequency of occurrence proportions and 95% confidence limits for 25 handwritten numeral characteristics. A total of 277 intercharacter pairs of handwritten numeral characteristics were cross‐analyzed for interdependence. The results were that 72.92% of all intercharacter pairs had a coefficient of correlation between −0.2 and +0.2 in this study. [ABSTRACT FROM AUTHOR]

A method to writer verification based on handwritten stroke analysis is presented. The proposed descriptors correspond to an estimation of the pressure applied when writing using the grayscale image of the stroke. These descriptors are obtained from individual and simple graphemes, in contrast with the complexity of the handwritten stroke used in the signature processing systems. In addition, a study is presented which suggests that the combination of descriptors of simple characters improves the recognition capacity of the method. The descriptors considered correspond to different accuracy degrees of pressure distribution representation. Specifically, from the simplest representation to a more complex one, the descriptors proposed are as follows: the width of the stroke, the gray level of the grapheme skeleton, the average of the gray levels on the perpendicular line to the skeleton, and the approximation transformation coefficients of the area of the grapheme. The advantage of these descriptors is that they are invariant to scale and rotation. The descriptors performance was assessed using the original images and also reduced versions based on traditional methods such as Principal Component Analysis and Discrete Cosine Transform. For the evaluation, a one-vs-all scheme was considered which is consistent with the problem of identity verification. It was implemented with Support Vector Machine classifiers trained with K-Fold Cross Validation. The efficient search of SVM hyperparameters was performed with the heuristic optimization algorithm Simulated Annealing. The evaluation of individual simple characters gives a high average of hits and the combination of characters even improves the performance, getting closer to 100% of hits in identity verification. Qualitative and quantitative comparison with other methods and descriptors has been also carried out with satisfactory results. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Babylon University is the property of Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In the Anglophone sphere, according to popular and most academic understandings, the term "ideograph" is regarded as an unproblematic synonym of 漢字 hànzì 'Chinese character.' On graphological grounds, i.e. as applied to writing systems, it can easily be shown that the concept of "ideograph" is both theoretically incoherent and practically unfeasible (McDonald 2016); while historically it is clear that the notion was founded on an imperfect understanding of Chinese characters as a writing system, and grew out of a European obsession with the notion of a "universal character" at a particular historical moment (Mungello 1985; Saussy 2001). Nevertheless the concept has become deeply embedded in European understandings of Chinese language and culture, to the extent that it is, in effect, a valuable conceptual possession of Western modernity (Bush 2010), and promoted alike by those with a detailed knowledge of Chinese writing, such as H. G. Creel (1936), as by those in blissful ignorance of it, like Jacques Derrida (1967/1976). In the Sinophone sphere, while for most practical purposes, as well as in a large proportion of scholarly work, more grounded understandings of Chinese characters as a writing system operate either implicitly or explicitly, the traditional emphasis on characters as a link between civilization and the cosmos (O'Neill 2013), as well as a long tradition of pedagogical "just so stories" about the construction of individual characters (e.g., Zuo 2005), provide a key point of contact with Western notions of the "ideograph" as symbolizing not a word, but an idea or an object. The situation may thus be described involving a type of inversion of the phenomenon of faux amis or "false friends," where two different words are understood as being more or less synonymous; or alternatively as an example of Lydia Liu's (2004) notion of a cross-lingual "supersign" where two comparable terms exercise an influence on each other across linguistic and cultural boundaries. This article will attempt to trace the genealogy of these complex and overlapping notions, and see what differing understandings of Chinese characters have to tell us about notions of cultural specificity, cultural production, and cross-cultural (mis-)communication in the contemporary globalized world. [ABSTRACT FROM AUTHOR]

Describes the characteristics of soldier of George Armstrong Custer through a graphoanalysis. Indication of stability and maturity in the emotions of Custer based on the degree of uniformity in the slant of his writing; Loyalty of Custer to his convictions; Career background of Custer as a military officer.

[Display omitted] • A novel system to understand ancient book genesis via handwriting attribution. • Machine Learning and spectroscopic benchmarks. • ' Clavis Prophetarum ' by Antonio Vieira. • Authors' classification and chronological succession of interventions. • Impact on handwriting authentication and attribution. Machine learning is a key branch of artificial intelligence that uses models to interpret data patterns. Herein, we demonstrate a novel approach that combines X-ray fluorescence and Fourier transform infrared spectroscopies as well as machine learning to provide insights into the genesis of an ancient manuscript by recognising different inks used for author attribution. The procedure was successfully applied to Clavis Prophetarum , a manuscript authored by Antonio Vieira (1608–1697), considered one of the 'fathers' of the Portuguese language. This original manuscript, previously considered lost, was recently discovered at the Historical Archive of the Pontifical Gregorian University in Rome. Unsupervised and supervised techniques such as principal component analysis and singular vector machine were used to distinguish between different inks made with similar recipes using spectroscopic benchmarks. On the one hand, sulphur and iron were identified as elemental benchmarks and on the other hand, Arabic gum, oak gall and iron gall precipitates were identified as the main ingredients via molecular fingerprints, which differ in their proportions. The methodology, which does not require data pre-processing, allows the handwriting (i.e., authorship) attribution of small signs and revisions, which cannot be attributed through standard methods. The supervised model enabled assigning 66% of the previously unassigned handwriting and strokes, identifying four main groups. These results, together with macroscopical observations and historical information, recognised Group 2 as the main handwriting assigned to the first author, Antonio Vieira. Group 1 was attributed to P. C. A. Casnedi , who performed the drafting and revisions in a well-defined period and introduced the first (most ancient) page numbering. Group 4 was attributed to P. A. Bonucci , the last collaborator of Antonio Vieira , who reorganised the numbering of quires, suggesting that this author was the last one who worked on the manuscript. A particular section of the book (Book 3, Chapter 1) was assigned to Group 3 and was attributed to an unknown author. This study is expected to have an impact in the field of authentication, with potential applications to ancient and modern manuscripts and handwriting analysis. [ABSTRACT FROM AUTHOR]

The graphology is a quasi-science (pseudo- science). It is considered to be one of the unconventional methods for human resources selection in the organizations. The graphologists believe that on the base of the handwriting and on the written material a psychologic personal's profile can be made. With the graphological analyses numerous features of the handwriting can be interpreted such as: the initial and final of one word' emphasis, correctness and readability of the words, letter' s form, letter's size, hand pressure on the paper, distance between the lines, writings course and other. This method is not scientifically approved, although it is used in the organizations in a lot of West European countries and in USA as a tool for selection of human resources. In the most of the announces for vacancies the candidates are required to fulfill the application forms in hand.

Previous studies of Sherlock Holmes fandom have concentrated on fan letters as being exemplary of the early beginnings of the Great Game: a fantasy played by fans that acts upon the belief that Sherlock Holmes exists. Fans, while fully comprehending that it is indeed a fantasy or a game, perform fan activities such as historical and literary analysis as if Holmes were real. This paper shifts the focus away from letter writing as the central means of the expression of this ironic belief and looks at the example of collecting autographs as a means of celebration of the canon. It places the autograph in its historical context of being the meeting point between the remnants of the Romantic theory of genius, the development of pseudosciences such as the interpretation of handwriting, and the literary, cultural, and commercial landscape in which Holmes appeared.

Chapter three explores the Shakespeare homes and households contrasting Shakespeare to other indentured and impoverished writers and concluding, following Germaine Greer and others, that Anne was a hard-working partner to her husband. The book consists of five chapters analysing five moments and five dates: 23 January 1577, "Shakespeare's Father"; 27 November 1582, "Shakespeare's Wedding"; 4 May 1597, "Shakespeare's Home"; 25 March 1616, "Shakespeare's Will"; and 25 April 1616, "Shakespeare's Monument". There have been lots of speculative attempts to forge links between Shakespeare's life and art. [Extracted from the article]

In this paper we introduce Eddy, a new open-source tool for the graphical editing of OWL 2 ontologies. Eddy is specifically designed for creating ontologies in GRAPHOL, a completely visual ontology language that is equivalent to OWL 2. Thus, in Eddy ontologies are easily drawn as diagrams, rather than written as sets of formulas, as commonly happens in popular ontology design and engineering environments. This makes Eddy particularly suited for usage by people who are more familiar with diagramatic languages for conceptual modeling rather than with typical ontology formalisms, as is often required in nonacademic and industrial contexts. Eddy provides intuitive functionalities for specifying GRAPHOL diagrams, guarantees their syntactic correctness, and allows for exporting them in standard OWL 2 syntax. A user evaluation study we conducted shows that Eddy is perceived as an easy and intuitive tool for ontology specification. [ABSTRACT FROM AUTHOR]

Automatic segmentation-free and training-free word spotting is a challenging task due to the large intra-class variability of handwritten shapes and the need to process the whole document image. In this work, a novel unsupervised hierarchical handwriting representation is introduced, where the spherical k-means algorithm is used to learn a hierarchy of features for representing document images. A matching system is then employed for word spotting, which consists of two stages: (1) a fast pre-selection stage applying a sliding-window approach over compressed document image representations, and (2) a re-ranking stage based on a discriminative description that encodes the spatial layout of local features. The proposed approach is evaluated using three well-known benchmark datasets, the Lord Byron (LB), the George Washington (GW) and the IAM datasets. Results show our method to yield competitive performance compared to state-of-the-art approaches for segmentation-free and training-free word spotting. In addition, since our proposed framework has a low computational and memory complexity, it can be applied to large datasets. [ABSTRACT FROM AUTHOR]

Forensic science has traditionally focused the majority of its resources and objectives towards addressing Court-related questions. However, this view restricts the contribution of forensic science to one process and results in a loss of information as the investigative and intelligence roles are largely neglected. A forensic science discipline suffering from this imbalance is handwriting examination, which may be characterised as a time consuming and subjective process that is mostly carried out towards the end of the investigation for the purpose of judicial proceedings. Individual and habitual characteristics are the major handwriting features exploited, however alternate information concerning the author's native language could potentially be used as a key element in an intelligence framework. This research focussed on the detection of characteristics that differentiate Vietnamese and English Australian writers based on their English handwriting. The study began with the extraction of handwriting characteristics from the writing of people from the two populations. The data was analysed using a logistic regression model and a classification and regression tree (CRT). Each recognised four class characteristics that were capable of distinguishing between the two nationalities. The logistic regression and CRT models were both capable of correctly predicting 93% of cases. Their predictive capabilities were then tested and supported using blind exemplars in order to mirror casework settings. It appeared that when using their respective class characteristics, the two models were capable of differentiating English Australians from Vietnamese in the data set. This proof of concept research demonstrated the plausibility of exploiting this additional information from a handwriting trace and taking advantage of it in an intelligence-led framework. [ABSTRACT FROM AUTHOR]

Research on intra-speaker variation is scarce within the field of historical sociolinguistics, particularly with regard to German data. This paper examines whether the major approaches of modern sociolinguistics in this area, namely attention to speech, audience design, and speaker design, can be applied to the analysis of historical material. The paper focuses on a comparative analysis of eleven letters written between 1891 and 1905 by a mentally ill day-labourer at the southern German psychiatric hospital of Kaufbeuren. The combination of qualitative and quantitative methods for the examination of two graphemic variables provides evidence for all three factors of stylistic variation. In addition, the deterioration of the writer's health appears to give rise to language change in his later letters; and this change is shown to be highly statistically significant. The paper thus offers new perspectives on the analysis of intra-speaker variation in historical data in particular and for language history 'from below' in general and demonstrates the need to reevaluate the linguistic competence of lower-class writers of the past. [ABSTRACT FROM AUTHOR]

Character recognition is one of the challenging tasks of pattern recognition and machine learning arena. Though a level of saturation has been obtained in machine printed character recognition, there still remains a void while recognizing handwritten scripts. We, in this paper, have summarized all the existing research efforts on the recognition of printed as well as handwritten Odia alphanumeric characters. Odia is a classical and popular language in the Indian subcontinent used by more than 50 million people. In spite of its rich history, popularity and usefulness, not much research efforts have been made to achieve human level accuracy in case of Odia OCR. This review is expected to serve a benchmark reference for research on Odia character recognition and inspire OCR research communities to make tangible impact on its growth. Here several preprocessing methodologies, segmentation approaches, feature extraction techniques and classifier models with their respective accuracies so far reported are critically reviewed, evaluated and compared. The shortcomings and deficiencies in the current state-of-the-art are discussed in detail for each stage of character recognition. A new handwritten alphanumeric character database for Odia is created and reported in this paper in order to address the paucity of benchmark Odia database. From the existing research work, future research paradigms on Odia character recognition are suggested. We hope that such a comprehensive survey on Odia character recognition will serve its purpose of being a solid reference and help creating high accuracy Odia character recognition systems. [ABSTRACT FROM AUTHOR]

Text-independent handwriting identification methods require that features such as texture are extracted from lengthy document image; while text-dependent handwriting identification methods require that the contents of the documents being compared are identical. In order to overcome these confinements, this paper presents a novel Chinese handwriting identification technique. First, Chinese characters are segmented from handwriting document, then keywords are extracted based on matching and voting of local features of character. Then the same-content keywords are used to build training sets, and these training sets of two documents are compared. Because the keywords are similar to signature, the handwriting identification problem is transformed into signature verification problem. Experiments on HIT-MW, HIT-SW and CASIA show this method outperforms many text-independent handwriting identification methods. [ABSTRACT FROM AUTHOR]

This paper presents a system to predict gender of individuals from offline handwriting samples. The technique relies on extracting a set of textural features from handwriting samples of male and female writers and training multiple classifiers to learn to discriminate between the two gender classes. The features include local binary patterns (LBP), histogram of oriented gradients (HOG), statistics computed from gray-level co-occurrence matrices (GLCM) and features extracted through segmentation-based fractal texture analysis (SFTA). For classification, we employ artificial neural networks (ANN), support vector machine (SVM), nearest neighbor classifier (NN), decision trees (DT) and random forests (RF). Classifiers are then combined using bagging, voting and stacking techniques to enhance the overall system performance. The realized classification rates are significantly better than those of the state-of-the-art systems on this problem validating the ideas put forward in this study. [ABSTRACT FROM AUTHOR]

Recognition of handwritten characters is a challenging task. Variations in writing styles from one person to another, as well as for a single individual from time to time, make this task harder. Hence, identifying the local invariant patterns of a handwritten character or digit is very difficult. These challenges can be overcome by exploiting various script specific characteristics and training the OCR system based on these special traits. Finding ubiquitous invariant patterns and peculiarities, applicable for handwritten characters or digits of multiple scripts, is much more difficult. In the present work, a non-explicit feature based approach , more specifically, a multi-column multi-scale convolutional neural network (MMCNN) based architecture has been proposed for this purpose. A deep quad-tree based staggered prediction model has been proposed for faster character recognition. These denote the most significant contributions of the present work. The proposed methodology has been tested on 9 publicly available datasets of isolated handwritten characters or digits of Indic scripts. Promising results have been achieved by the proposed system for all of the datasets. A comparative analysis has also been performed against some of the contemporary OCR systems to prove the superiority of the proposed system. We have also evaluated our system on MNIST dataset and achieved a maximum recognition accuracy of 99.74%, without any data augmentation to the original dataset. [ABSTRACT FROM AUTHOR]

Machine recognition of a handwritten mathematical expression (HME) is challenging due to the ambiguities of handwritten symbols and the two-dimensional structure of mathematical expressions. Inspired by recent work in deep learning, we present Watch, Attend and Parse (WAP), a novel end-to-end approach based on neural network that learns to recognize HMEs in a two-dimensional layout and outputs them as one-dimensional character sequences in LaTeX format. Inherently unlike traditional methods, our proposed model avoids problems that stem from symbol segmentation, and it does not require a predefined expression grammar. Meanwhile, the problems of symbol recognition and structural analysis are handled, respectively, using a watcher and a parser. We employ a convolutional neural network encoder that takes HME images as input as the watcher and employ a recurrent neural network decoder equipped with an attention mechanism as the parser to generate LaTeX sequences. Moreover, the correspondence between the input expressions and the output LaTeX sequences is learned automatically by the attention mechanism. We validate the proposed approach on a benchmark published by the CROHME international competition. Using the official training dataset, WAP significantly outperformed the state-of-the-art method with an expression recognition accuracy of 46.55% on CROHME 2014 and 44.55% on CROHME 2016. [ABSTRACT FROM AUTHOR]

Background The majority of patients with Parkinson's disease ( PD) have handwriting abnormalities. Micrographia (abnormally small letter size) is the most commonly reported and easily detectable handwriting abnormality in patients with PD. However, micrographia is perhaps the tip of the iceberg representing the handwriting abnormalities in PD. Digitizing tablet technology, which has evolved over the last 2 decades, has made it possible to study the pressure and kinematic features of handwriting. This has resulted in a surge of studies investigating graphomotor impairment in patients with PD. Methods The objectives of this study were to review the evolution of the kinematic analysis of handwriting in PD and to provide an overview of handwriting abnormalities observed in PD along with future directions for research in this field. Articles for review were searched from the PubMed and SCOPUS databases. Results Digitizing tablet technologies have resulted in a shift of focus from the analysis of only letter size to the analysis of several kinematic features of handwriting. Studies based on the kinematic analysis of handwriting have revealed that patients with PD may have abnormalities in velocity, fluency, and acceleration in addition to micrographia. The recognition of abnormalities in several kinematic parameters of handwriting has given rise to the term PD dysgraphia. In addition, certain kinematic properties potentially may be helpful in distinguishing PD from other parkinsonian disorders. Conclusion The journey from micrographia to PD dysgraphia is indeed a paradigm shift. Further research is warranted to gain better insight into the graphomotor impairments in PD and their clinical implications. [ABSTRACT FROM AUTHOR]

Handwriting represents an important modality in both biometric and forensic domains. while the first field appears to be a well-studied area with many approaches for acquisition, feature extraction and classification, the latter is rather novel with respect to digitised, automated methods. In prior works, authors of this article have shown that forensic handwriting traces can be processed by means of high-resolution 2D/3D surficial scanners. These devices allow the acquisition at a vertical resolution down to a few nanometres. Pre-processing methods have been identified, which allow for spatial segmentation of writing traces and for de-noising of 2D and 3D data, leading to a clear visual enhancement of the writing traces based on topography information. Further, authors have suggested a novel benchmarking method for forensic trace analysis based on feature sets originally suggested for biometric handwriting and comparing the forensic recognition performance by means of equal error rates, achieved from biometric sensors and forensic 2D/3D sensors in parallel. This article summarises and extents these works in two main aspects: on one side, it presents significantly extended experiments with respect to test set size and feature sets utilised for classification. On the other side, authors suggest new optimisation approaches to the segmentation algorithm. [ABSTRACT FROM AUTHOR]

One of the commonly used methods for determining the authenticity of the painting is the analysis of signature placed on it. However, unmistakable confirmation of authenticity may apply only to signatures of sufficiently high quality. The article indicates, from a handwriting expert viewpoint, which properties of signatures are significant to their identification, and which are not, and therefore, that in some cases, despite the correspondence of signature with the exemplars, conclusion about its authenticity is invalid. [ABSTRACT FROM AUTHOR]

The author discusses the authorship of an anonymous English sonnet found in the back of a collection of Spanish plays. He mentions possible candidates for authors and uses a graphological analysis to propose the English author Henry Neville (1619-1694) as the most likely person to have written the poem.