Input Character Research Articles

Motion Analysis of Visual Line in Eye-gaze-based Character Input Process Using an Onscreen Keyboard

Motion Analysis of Visual Line in Eye-gaze-based Character Input Process Using an Onscreen Keyboard

Lexical Analysis in Content Management System Details

In cognitive science, understanding language by humans starts with recognition. Without the phase, understanding languages become a very cumbersome task. The task of the lexical analyzer is to read the various input characters grouping them into lexemes and producing an output of a sequence of tokens. But before we discuss lexical analysis further, we should have an overview of this research. Lexical analysis is best described as tokenization that converts a sequence of characters (program) into tokens with identifiable meanings. This study aims to look at the various terms or words related to lexical structure, purpose, and how they are applied to get the required result. The lexical analysis offers researchers an idea of the structural aspect of computer language and its semantic content. The work also talks about the advantages and disadvantages of lexical analysis.

Handwritten Text Recognition using Machine Learning Techniques in Application of NLP

Handwriting Detection is a technique or ability of a Computer to receive and interpret intelligible handwritten input from source such as paper documents, touch screen, photo graphs etc. Handwritten Text recognition is one of area pattern recognition. The purpose of pattern recognition is to categorizing or classification data or object of one of the classes or categories. Handwriting recognition is defined as the task of transforming a language represented in its spatial form of graphical marks into its symbolic representation. Each script has a set of icons, which are known as characters or letters, which have certain basic shapes. The goal of handwriting is to identify input characters or image correctly then analyzed to many automated process systems. This system will be applied to detect the writings of different format. The development of handwriting is more sophisticated, which is found various kinds of handwritten character such as digit, numeral, cursive script, symbols, and scripts including English and other languages. The automatic recognition of handwritten text can be extremely useful in many applications where it is necessary to process large volumes of handwritten data, such as recognition of addresses and postcodes on envelopes, interpretation of amounts on bank checks, document analysis, and verification of signatures. Therefore, computer is needed to be able to read document or data for ease of document processing.

A robot calligraphy writing method based on style transferring algorithm and similarity evaluation

This paper proposes a robot calligraphy writing method based on style transfer algorithm, which can transfer the art style of Chinese font and maintain the imitation accuracy of the calligraphy. A prototypical similarity evaluation approach is also presented to analyze the calligraphy writing effect, including the similarity ratio of balance, inclination and writing intensity. The robot writing system mainly consists of a six-DOF robot, manipulator, Chinese brush and PC controller. Firstly, input character images are transformed into target style font through training and style transferring process based on generative adversarial networks method. Then, the description parameters of the character images with target style are extracted to control the robot calligraphy writing process precisely. Experimental results show that the minimum similarity between the styles of robot writing characters and target characters is larger than 0.75. The proposed method shows good calligraphy writing effect, which can be used for various calligraphy training processes and trajectory planning applications.

Developing The Pointer Backward-Forward Algorithm In Token Of Test In Text To Know The Level Of Individual Depression

The way you move and sleep, interact with people around you, depression change everything. This even looks at the way you talk and express yourself in writing. Sometimes this “depression language” can have a strong effect to others. Natural Language Processing (NLP) is one of the fields of computer science, artificial intelligence, and language (linguistics) related to the interaction between computers and natural human languages, such as Indonesian or English. The main objective of the NLP study is to make a machine that is able to know and understand the meaning of language, lexical analysis has the role of reading input characters and generating output tokens and making spaces, tabs, newlines and connecting rows of programs. However, the problems will occur when lexical analyzers where lexical is not able to determine when there are misspellings on tokens. Therefore, with the development of the backward-forward pointer algorithm, it is expected that in the future it will be easier to analyze both the words in front, in the middle and behind, so that the machine can quickly determine the individual depression level of speech tokens and speech tones.

Gestural flick input-based non-touch interface for character input

A non-touch character input is a modern system for communication between humans and computers that can help the user to interact with a computer, a machine, or a robot in unavoidable circumstances or industrial life. There have been many studies in the field of touch and non-touch character input systems (i.e., hand gesture languages), such as aerial handwriting, sign languages, and the finger alphabet. However, many previously developed systems require substantial effort in terms of learning and overhead processing for character recognition. To address this issue, this paper proposes a gesture flick input system that offers a quick and easy input method using a hygienic and safe non-touch character input system. In the proposed model, the position and state of the hands (i.e., open or closed) are recognized to enable flick input and to relocate and resize the on-screen virtual keyboard for the user. In addition, this system recognizes hand gestures that perform certain motion functions, such as delete, add a space, insert a new line, and select language, an approach which reduces the need for recognition of a large number of overhead gestures for the characters. To reduce the image-processing overhead and eliminate the surrounding noise and light effects, body index skeleton information from the Kinect sensor is used. The proposed system is evaluated based on the following factors: (a) character selection, recognition and speed of character input (in Japanese hiragana, English, and numerals); and (b) accuracy of gestures for the motion functions. The system is then compared to state-of-the-art algorithms. A questionnaire survey was also conducted to measure the user acceptance and usability of this system. The experimental results show that the average recognition rates for characters and motion functions were 98.61% and 97.5%, respectively, thus demonstrating the superiority of the proposed model compared to the state-of-the-art algorithms.

Telugu Character Recognition using Adaptive Fuzzy Membership Functions With Adaptive Genetic Algorithm Based Techniques

A novel Telugu character recognition technique is proposed in this paper where the given Telugu handwritten document is processed by normalizing the document and removing the noise. Then slant detection followed by correction process is conceded using the bilinear interpolation method to get more accurate result. Thus the de-skewed documents text lines and characters are separated by making use of Adaptive Histogram Equalization (AHE). In the next stage, the characteristics of the segmented characters are mined with the help of the zoning method. In zoning method, an adaptive fuzzy membership function will be developed by the Adaptive Genetic Algorithm (AGA). By using AGA in zoning method the characteristics are mined from the separated characters. The mined structures are applied to the Feed Forward Back Propagation Neural Network (FFBNN) for accomplishing the learning process. During testing, more number of handwritten segmented Telugu characters will be set to the FFBNN to verify whether the input character is recognized or not. Thus, the proposed method has given more accurate recognition results by using our proposed adaptive fuzzy membership function with AGA method. The proposed method performance is evaluated by getting more number of handwritten Telugu documents and compared with the GA-FFBNN and FFBNN.

Camera Captured Handwritten Kannada Character Recognition

Optical Character Recognition (OCR) is an automatic reading of text components that are optically sensed to translate human-readable characters into machine-readable codes. In handwritten the style of writing vary from person to person, so it is very challenging task to segment and recognize the characters. In this paper we are proposing segmentation and feature extraction techniques to recognise camera captured, handwritten Kannada documents. The segmentation is done by using projection profile technique & Connected Component Analysis (CCA). The pre-processing technique to detect the edges of Kannada character, we have proposed our own technique by combining of Sobel and Canny edge detection. The feature selection and extraction is done in two level, global and local features. Global features are extracted from entire image. In local feature extraction we divided an input character image in to four quadrate based on centroid of character and we will extract local features from all quadrates rather than whole image. We have used Support vector machine (SVM) to classify the handwritten Kannada characters. To evaluate the efficiency of proposed system we have used KHDD dataset, our own document and character dataset. The experimental results shows that our proposed features selection and extraction achieved 96.31% of accuracy, results are encouraging.

Aperiodic Stochastic Resonance in the Fractional-Order Bistable System

The aperiodic stochastic resonance (ASR) in the bistable fractional-order system is further studied when the fractional-order lies in the interval (0, 2). In previous works, the ASR can only process aperiodic binary signal with large pulse width. However, for the signal with small pulse width, the method cannot work. Actually, the signals with small pulse width are also common in the information transmission field. It greatly limits the application of the fractional stochastic resonance. Hence, we mainly focus on the enhancement of aperiodic binary signal with small pulse width. To solve the aforementioned technical problem, the general scale transformation is introduced, which allows us to achieve the ASR successfully. By this method, the equivalent system with large system parameters is able to match the input character signal with arbitrary small pulse width well, where the scale parameter is a key to achieve resonance. During the process, the fractional-order system presents rich dynamical behaviors in processing the aperiodic binary signals. Especially, as the order increases, the output signal at optimal noise intensity might be better and be more similar to the input one. This indicates the fractional order can optimize the stochastic resonance. The results might provide some reference to the engineering field, such as digital transmission and image processing field.

Sebacinoids within rhizospheric fungal communities associated with subsistence farming in the Congo Basin: a needle in each haystack.

The unique ecosystem of the Congolese rainforest has only scarcely been explored for its plant-fungal interactions. Here, we characterized the root fungal communities of field-grown maize and of Panicum from adjacent borders in the Congo Basin and assessed parameters that could shape them. The soil properties indicated that comparable poor soil conditions prevailed in fields and borders, illustrating the low input character of local subsistence farming. The rhizosphere fungal communities, dominated by ascomycetous members, were structured by plant species, slash-and-burn practices and soil P, pH and C/N ratio. Examining fungi with potential plant growth-promoting abilities, the glomeromycotan communities appeared to be affected by the same parameters, whereas the inconspicuous symbionts of the order Sebacinales seemed less susceptible to environmental and anthropogenic factors. Notwithstanding the low abundances at which they were detected, sebacinoids occurred in 87% of the field samples, implying that they represent a consistent taxon within indigenous fungal populations across smallholder farm sites. Pending further insight into their ecosystem functionality, these data suggest that Sebacinales are robust root inhabitants that might be relevant for on-farm inoculum development within sustainable soil fertility management in the Sub-Saharan region.

A high-performance CNN method for offline handwritten Chinese character recognition and visualization

Recent researches introduced fast, compact and efficient convolutional neural networks (CNNs) for offline handwritten Chinese character recognition (HCCR). However, many of them did not address the problem of network interpretability. We propose a new architecture of a deep CNN with high recognition performance which is capable of learning deep features for visualization. A special characteristic of our model is the bottleneck layers which enable us to retain its expressiveness while reducing the number of multiply-accumulate operations and the required storage. We introduce a modification of global weighted average pooling (GWAP) - global weighted output average pooling (GWOAP). This paper demonstrates how they allow us to calculate class activation maps (CAMs) in order to indicate the most relevant input character image regions used by our CNN to identify a certain class. Evaluating on the ICDAR-2013 offline HCCR competition dataset, we show that our model enables a relative 0.83% error reduction while having 49% fewer parameters and the same computational cost compared to the current state-of-the-art single-network method trained only on handwritten data. Our solution outperforms even recent residual learning approaches.

Hybrid Attention for Chinese Character-Level Neural Machine Translation

This paper proposes a novel character-level neural machine translation model which can effectively improve the Neural Machine Translation (NMT) by fusing word and character attention information. In our work, the bidirectional Gated Recurrent Unit (GRU) network is utilized to compose word-level information from the input sequence of characters automatically. Contrary to traditional NMT models, two kinds of different attentions are incorporated into our proposed model: One is the character-level attention which pays attention to the original input characters; The other is the word-level attention which pays attention to the automatically composed words. With the two attentions, the model is able to encode the information from the character level and word level simultaneously. We find that the composed word-level information is compatible and complementary to the original input character-level information. Experimental results on Chinese-English translation tasks show that the proposed model can offer a boost of up to +1.92 BLEU points over the traditional word based NMT models. Furthermore, our translation performance is also comparable to the latest outstanding models, including the state-of-the-art.

An Asynchronous Hybrid Spelling Approach Based on EEG-EOG Signals for Chinese Character Input.

In this paper, we presented a novel asynchronous speller for Chinese sinogram input by incorporating electroencephalography (EOG) into the conventional electroencephalography (EEG)-based spelling paradigm. An EOG-based brain switch was used to activate a classic row-column P300-based speller only when spelling was needed, enabling an asynchronous operation of the system. Then, the user could input sinograms by alternately performing P300 and double-blink tasks until he or she intended to stop spelling. With the incorporation of an EOG detector, the system achieved rapid sinogram input. In addition to asynchronous operation, the performance of the proposed speller was compared with that achieved by a P300-based method alone across 18 subjects. The proposed system showed a mean communication speed of approximately 2.39 sinograms per minute, an increase of 0.83 sinograms per minute compared with the P300-based method. The preliminary online performance indicated that the proposed paradigm is a very promising approach for practical Chinese sinogram input application. This system may also be expanded to users whose languages are written in logographic scripts to serve as an assistive communication tool.

SliT: Character input method for smart watch with low screen occupancy

SliT: Character input method for smart watch with low screen occupancy

A method of character input for the user interface with a low degree of freedom

In recent times, smart devices equipped with small touch panels have become very popular. Many such smart devices use a software keyboard for character input. Unfortunately, software keyboards have a limitation: the number of buttons and the input degrees of freedom remain the same, because a button and an input value correspond one-to-one. Thus, if we reduce the screen size while the button size remains the same, the number of buttons must decrease. Alternatively, if we maintain the number of buttons and reduce the screen size, the size of the button decreases, making input increasingly difficult. In this study, we investigate a new character input method that is specifically adapted for use on small screens. The proposed input interface has 4 × 2 operational degrees of freedom and consists of four buttons and two actions. By handling two operations as one input, 64 input options are secured. Additionally, we experimentally evaluate the proposed character input user interface deployed on a smart device. The proposed method enables an input of approximately 25 characters per minute, and it shows robust input performance on a small screen compared to previous software methods. Thus, the proposed method is better suited to small screens than were previous methods.

Appetite for Growth: Challenges to Scale for Food and Beverage Makers in Three U.S. Cities

Food and beverage (FaB) manufacturing represents a promising opportunity for small-scale “makers” and local economic development. The growth of entrepreneurial maker businesses can be understood in terms of segmentation of market demand, emergence of new intermediaries, and availability of affordable production infrastructure. Yet the ease of starting maker businesses stands in contrast with the challenges of achieving growth and scale as a manufacturer. Through semistructured interviews with 31 FaB makers in Chicago, New York City, and Portland, Oregon, the authors analyze the challenges facing maker–entrepreneurs in this sector. The authors find that the everyday character of food and the relative ubiquity of food production infrastructure helps makers get their start, but that the unique character of food inputs and distribution networks pose distinct challenges and opportunities as they grow. Economic development efforts to support FaB makers should focus on nurturing local demand, developing food-oriented intermediaries, and ensuring affordable production space.

Analisis Performa Rasio Kompresi Pada Metode Differensiasi ASCII Dan Lempel Ziv Welch (LZW)

ASCII differentiation is a compression method that utilizes the difference value or the difference between the bytes contained in the input character. Technically, the ASCII differentiation method can be done using a coding dictionary or using windowing block instead of the coding dictionary. Previous research that has been carried out shows that the ASCII differentiation compression ratio is good enough but still needs to be analyzed on performance from the perspective of the compression ratio of the method compared to other methods that have been widely used today. In this study an analysis of the comparison of the ASCII Difference method with other compression methods such as LZW will be carried out. The selection of LZW itself is done by reason of the number of data compression applications that use the method so that it can be the right benchmark. Comparison of the compression ratio performed shows the results of ASCII differentiation have advantages compared to LZW, especially in small input characters. Whereas in large input characters, LZW can optimize the probability of pairs of characters that appear compared to ASCII differentiation which is glued to the difference values ​​in each block of input characters so that in large size characters LZW has a greater compression ratio compared to ASCII differentiation.

CamK: Camera-Based Keystroke Detection and Localization for Small Mobile Devices

Because of the smaller size of mobile devices, text entry with on-screen keyboards becomes inefficient. Therefore, we present CamK, a camera-based text-entry method, which can use a panel (e.g., a piece of paper) with a keyboard layout to input text into small devices. With the built-in camera of the mobile device, CamK captures images during the typing process and utilizes image processing techniques to recognize the typing behavior, i.e., extract the keys, track the user's fingertips, detect, and locate keystrokes. To achieve high accuracy of keystroke localization and low false positive rate of keystroke detection, CamK introduces the initial training and online calibration. To reduce the time latency, CamK optimizes computation-intensive modules by changing image sizes, focusing on target areas, introducing multiple threads, removing the operations of writing or reading images. Finally, we implement CamK on mobile devices running Android. Our experimental results show that CamK can achieve above 95 percent accuracy in keystroke localization, with only a 4.8 percent false positive rate. When compared with on-screen keyboards, CamK can achieve a 1.25X typing speedup for regular text input and 2.5X for random character input. In addition, we introduce word prediction to further improve the input speed for regular text by 13.4 percent.

Computational design of transformables

AbstractWe present a computational approach to designing transformables, physical characters that can shape‐shift to take on vastly different forms. The design process begins with a morphological description of an input character and a target object that it should transform into. Guided by a set of objectives that model the core attributes of desirable transformable designs, optimized embeddings are interactively generated. Intuitively, embeddings represent tightly folded character configurations that fit within the target object. From any feasible embedding, skin meshes are then generated for each body part of the character. The process for generating these 3D models is based on a segmentation of the target object, which is achieved through a growth‐based model applied to a multiple level set representation of the transformable. A set of transformation‐aware post‐processing algorithms ensure the feasibility of the final designs. Building on this technical core, our computational design system provides many opportunities for users to inject their intuition and personal preferences into the process of creating transformables, while shielding them from tasks that are challenging and tedious. As a result, they can intuitively explore the vast space of design possibilities. We demonstrated the effectiveness of our computational approach by creating a variety of transformable designs, three of which we fabricate.

Training set extension for SVM ensemble in P300-speller with familiar face paradigm

P300-spellers are brain-computer interface (BCI)-based character input systems. Support vector machine (SVM) ensembles are trained with large-scale training sets and used as classifiers in these systems. However, the required large-scale training data necessitate a prolonged collection time for each subject, which results in data collected toward the end of the period being contaminated by the subject's fatigue. This study aimed to develop a method for acquiring more training data based on a collected small training set. A new method was developed in which two corresponding training datasets in two sequences are superposed and averaged to extend the training set. The proposed method was tested offline on a P300-speller with the familiar face paradigm. The SVM ensemble with extended training set achieved 85% classification accuracy for the averaged results of four sequences, and 100% for 11 sequences in the P300-speller. In contrast, the conventional SVM ensemble with non-extended training set achieved only 65% accuracy for four sequences, and 92% for 11 sequences. The SVM ensemble with extended training set achieves higher classification accuracies than the conventional SVM ensemble, which verifies that the proposed method effectively improves the classification performance of BCI P300-spellers, thus enhancing their practicality.