A Study of Novel Optical Character Recognition Algorithms

Optical Character Recognition has been an inseparable part of human life during everyday transactions. The OCR has extended its application areas in almost all fields viz. healthcare, finance, banking, entertainment, trading system, digital storage, and so on. In the recent past, handwriting recognition is one of the hardest study areas in the area of image processing. In this paper, the various techniques for converting textual content from number plates, printed, handwritten paper documents into machine code have been discussed. The transforming method used in all these techniques is known as OCR. The English OCR system is necessary for the conversion of various published books and other documents in English into human editable computer text files. The latest researches in this area have included methodologies that identify different fonts and styles of English handwritten scripts. As of date, even though a number of algorithms are available, it has its own pros and cons. Since the recognition of different styles and fonts in machine-printed and handwritten English script is the biggest challenge, this field is open for researchers to implement new algorithms that would overcome the deficiencies of its predecessors.

FORMALIZATION OF REGULATORY TEXTS

Modern information technologies provide text manipulation processes with high efficiency. First of all, this means storing, editing, and formatting texts and their components. Having achieved significant success in developing tools for content-free computer text processing, researchers faced problems with their content processing. Therefore, further steps in this direction are associated with the creation, among other things, of methods for automated purposeful manipulation of texts, taking into account their content. The analysis of works devoted to the study of the problems of formal presentation of texts and their subsequent use is carried out. Despite a number of successful projects, the challenges of solving the problem of the relationship between the content of the text and its meaning remain relevant. It seems that formalization of a General-purpose text while preserving its semantics is not feasible at this stage. However, there are types of texts that can be formalized while preserving their semantics. One of them is a regulatory text type, which is essentially a verbally expressed algorithm for a sequence of targeted actions. It is distinguished by logic and accuracy (lack of allegories), coherence and integrity, clarity, understandability (due to the lack of emotional coloring and figurative means), accessibility (due to the use of specific terminology). In other words, when developing regulatory texts, they usually try to display the mechanisms of the described actions as clearly as possible. Purpose: development of a method for formalizing a regulatory text while preserving its semantics. Methods: structural linguistics, representation of objects in the form of an ontology, constructive algorithms. The use of this method is demonstrated by describing the solution of a system of algebraic equations. Results: method for constructing a mathematical model of a regulatory text. Practical relevance: the application of the developed method makes it possible to develop software systems for building libraries of individual subject areas, develop tools for evaluating regulatory texts for their certainty, completeness, connectivity and other characteristics, as well as simulators and self-learning tools.

HYPERTEXT: SYNTHESIS OF DISCRETE AND CONTINUOUS MEDIA MESSAGE

In the article we interpret discrete and continuous message as interrupted and constant, limited and continual text, which has specific features and a number of differences between traditional (one-dimensional) text and hypertext (multidimensional). The purpose of this study is to define the concept of “hypertext”, consideration of its characteristics and features of the structure, similarities and differences with the traditional text, including the message in the media and communication. To achieve the goal of the study, we used a number of methods typical of journalism. Empirical analysis enabled a generalized description of the subject of study, which allowed to know it as a phenomenon. With the help of generalization the characteristic and specific regularities and principles of hypertext were studied. The system method is used to identify the dependence of each element of hypertext on its place in the text system as a whole. The retrospective method helped to understand the preconditions for the emergence of hypertext, to trace the dynamics of its development. General scientific methods (analysis, synthesis, induction, deduction) made it possible to formulate the conclusions of the study. Thanks to hypertext and the hypertext systems, the concept of virtual reality has gained tangible meaning. In hypertext space, virtuality organically complements reality. The state of virtuality, in this case, becomes the concept of hyperreality, and all this merges into a single whole in the space of computer text. Due to its volume and multidimensionality, hypertext can arouse scientific interest as an interdisciplinary discipline. In today’s world, the phenomenon of hypertext has been the subject of numerous discussions, conferences and research in the field of social communications, linguistics and psychology. Today, a significant number of organizations conduct large-scale research based on the concepts of hypertext associations and associative navigation.

EXAMINATION AS A MEANS OF ESTABLISHING THE FACTS AND CIRCUMSTANCES OF COMMISSION OF TRANSNATIONAL COMPUTER CRIMES

The article is noted that investigators are not able to track all technological changes in the field of information technology and to study the traces of this type of crime, special attention is paid to the use of examination of computer systems and computer media (order of the Ministry of Justice of Ukraine dated 08.10.98, No. 53/5). During the examination, it is advisable to solve the following problems: – identification, that is the diagnosis of system processes and system behavior; system identification; multivariate analysis and reconstruction of the circumstances of the event place (by methods of mathematical analysis and computer simulation); diagnostics of the functional purpose of individual elements of a computer system, an intelligent hacking system; identification of the author of the computer text (they seem more important for the investigation and the court); – non-identification, that is determination of the structure and functions of telecommunication networks and e-mail facilities; reconstruction and prediction of system behavior; determination of the reliability and resilience of computer systems; classifying information as software; classifying specific programs as harmful; definition of semantics and grammar of controversial texts; diagnostics and classification of printers, faxes, copy machines according to the text that was made from them. It is advisable in the expert’s conclusion to display the facts of fixing information traces about the actions of malicious programs and search for seized files, parts of files that were specially removed at the beginning of the review or accidentally during the review; results of verification of system, protection, and application logs using documents that govern the rules for archiving logs; audit results (operators, privileges, objects). To the conclusion, it is necessary to attach reports that were generated by the corresponding software, copies on machine media that were obtained during physical fixation. In the case of using a computer document as evidence, there is a need to specify: the means of collecting and processing information; type of system used; control tools that are built into the system for guaranteed detection and correction of errors, determining the level of professional training of individuals in the field of programming and working with computer equipment.

A Computerized Text and Cluster Analysis Approach to Psychotherapy Talk

This paper illustrates an analytical approach combining LIWC, a computer text-analytic application, with cluster analysis techniques to explore ‘language styles’ in psychotherapy across sessions in time. It categorizes session transcripts into distinct clusters or styles based on linguistic (di)similarity and relates them to sessional progression, thus providing entry points for further qualitative exploration. In the first step, transcripts of four illustrative therapist-client dyads were scored under ten LIWC variables including ‘analytic thinking’, ‘clout’, ‘authenticity’, ‘emotional tone’, and pronoun types. In the next step, agglomerative hierarchical clustering uncovered distinct session clusters that are differently distributed in each dyad. The relationships between these clusters and the chronological progression of sessions were then further discussed in context as contrastive exemplars. Applications, limitations and future directions are highlighted.

Bidirectional deep architecture for Arabic speech recognition

Nowadays, the real life constraints necessitates controlling modern machines using human intervention by means of sensorial organs. The voice is one of the human senses that can control/monitor modern interfaces. In this context, Automatic Speech Recognition is principally used to convert natural voice into computer text as well as to perform an action based on the instructions given by the human. In this paper, we propose a general framework for Arabic speech recognition that uses Long Short-Term Memory (LSTM) and Neural Network (Multi-Layer Perceptron: MLP) classifier to cope with the nonuniform sequence length of the speech utterances issued fromboth feature extraction techniques, (1)Mel Frequency Cepstral Coefficients MFCC (static and dynamic features), (2) the Filter Banks (FB) coefficients. The neural architecture can recognize the isolated Arabic speech via classification technique. The proposed system involves, first, extracting pertinent features from the natural speech signal using MFCC (static and dynamic features) and FB. Next, the extracted features are padded in order to deal with the non-uniformity of the sequences length. Then, a deep architecture represented by a recurrent LSTM or GRU (Gated Recurrent Unit) architectures are used to encode the sequences of MFCC/FB features as a fixed size vector that will be introduced to a Multi-Layer Perceptron network (MLP) to perform the classification (recognition). The proposed system is assessed using two different databases, the first one concerns the spoken digit recognition where a comparison with other related works in the literature is performed, whereas the second one contains the spoken TV commands. The obtained results show the superiority of the proposed approach.

Russian Punctuation as a Sign System

The Russian punctuation is a system of signs with its own functions and its own formal organization, different from the organization of alphabetic characters, numbers and other written signs of the Russian language. In terms of formal organization, punctuation marks differ from two-dimension characters in geometry and in onedimensionality or even zero-dimensionality. In terms of function, they are used as signs of articulation and organization of the text (as the metatext by A. Wierzbicka). Punctuation marks are located between graphic (linguistic-visual) and paragraphic (nonlinguistic visual) systems of writing. They perform their function in combination with the system of spaces (word space, arbitrary line end, empty part of the page, empty page) and paragraph tools. The punctuation is similar in function to road signs and computer text markup but unlike them punctuation marks are situated on the line alternately with the main objects of the writing.