Input Character Research Articles

Fast and Memory-Efficient Regular Expression Matching Using Transition Sharing

Scanning packet payload at a high speed has become a crucial task in modern network management due to its wide variety applications on network security and application-specific services. Traditionally, Deterministic finite automatons (DFAs) are used to perform this operation in linear time. However, the memory requirements of DFAs are prohibitively high for patterns used in practical packet scanning, especially when many patterns are compiled into a single DFA. Existing solutions for memory blow-up are making a trade-off between memory requirement and memory access of processing per input character. In this paper we proposed a novel method to drastically reduce the memory requirements of DFAs while still maintain the high matching speed and provide worst-case guarantees. We removed the duplicate transitions between states by dividing all the DFA states into a number of groups and making each group of states share a merged transition table. We also proposed an efficient algorithm for transition sharing between states. The high efficiency in time and space made our approach adapted to frequently updated DFAs. We performed several experiments on real world rule sets. Overall, for all rule sets and approach evaluated, our approach offers the best memory versus run-time trade-offs.

Wearable handwriting input device using magnetic field

In this paper an efficient technique using magnetic field is proposed for wearable handwriting input. This device requires mounting a permanent magnet onto fingertip and detecting the magnetic field generated by the magnet through magnetic sensors at the wrist of the other hand. The position of magnet is calculated by the vector of the magnetic field. And a method is proposed to avoid geomagnetic influence, using two magnetic sensors. Numerical methods are used to calculate the position of magnet with geomagnetism cancellation. Two numerical methods have been adopted and compared. A prototype device is made and we succeeded to get the trajectory of handwriting input character.

A Development of a System Enables Character Input and PC Operation via Voice for a Physically Disabled Person with a Speech Impediment

We have designed and implemented a PC operation support system for a physically disabled person with a speech impediment via voice. Voice operation is an effective method for a physically disabled person with involuntary movement of the limbs and the head. We have applied a commercial speech recognition engine to develop our system for practical purposes. Adoption of a commercial engine reduces development cost and will contribute to make our system useful to another speech impediment people. We have customized commercial speech recognition engine so that it can recognize the utterance of a person with a speech impediment. We have restricted the words that the recognition engine recognizes and separated a target words from similar words in pronunciation to avoid misrecognition. Huge number of words registered in commercial speech recognition engines cause frequent misrecognition for speech impediments' utterance, because their utterance is not clear and unstable. We have solved this problem by narrowing the choice of input down in a small number and also by registering their ambiguous pronunciations in addition to the original ones. To realize all character inputs and all PC operation with a small number of words, we have designed multiple input modes with categorized dictionaries and have introduced two-step input in each mode except numeral input to enable correct operation with small number of words. The system we have developed is in practical level. The first author of this paper is physically disabled with a speech impediment. He has been able not only character input into PC but also to operate Windows system smoothly by using this system. He uses this system in his daily life. This paper is written by him with this system. At present, the speech recognition is customized to him. It is, however, possible to customize for other users by changing words and registering new pronunciation according to each user's utterance.

Extracting fuzzy rules based on fusion of soft computing in oil exploration management

This paper proposed a self-learning, self-adapting algorithm (ANN-GA-Cascades) for extracting fuzzy rules, which is based on fusion of soft computing. We could use it to attain the fuzzy rules of oiliness in oil exploration: firstly, supervised learning of training sample is performed by using neural networks, with the inputs being the simplest well-logging attribute set which is relevant to the oiliness attributes, and the outputs being the corresponding oiliness partition Ck (dry layer, water layer, inferiority layer and oil layer). When the neural network attained precision or the maximum iteration steps, the kth output node of neural network will be the corresponding partition of decision character, with the output function being ψk=f(xi,(WG1)ij,(WG2)jk), in which (WG1)ij are the connection weights between input layer and hidden layer, (WG2)jk are the connection weights between hidden layer and output layer. Then, the genetic algorithm (GA) was used to randomly assemble the input character and ψk as the fitness function. In this way, the optimal chromosome will be the fuzzy rule of partition Ck. Finally, the empirical study application of this algorithm on oil well oilsk81 and oilsk83 of Jianghan oilfield in China has proved to be satisfactory.

An Efficient and User-friendly Sinhala Input Method Based on Phonetic Transcription

We propose an application-independent Sinhala character input method called Sri Shell with a principled key assignment based on phonetic transcription of Sinhala characters. A good character input method should fulfill two criteria, efficiency and user-friendliness. We have introduced several quantification methods to quantify the efficiency and user-friendliness of Sinhala character input methods. Experimental results prove the efficiency and user-friendliness of our proposed method.

Intensification of the Asian winter monsoon after 7.4 Ma: Grain-size evidence from the Linxia Basin, northeastern Tibetan Plateau, 13.1 Ma to 4.3 Ma

Grain-size studies of eolian deposits (loess and Red Clay) on the Chinese Loess Plateau have produced a detailed history of the Asian winter monsoon covering the last 8 Ma. This paper extends the gain-size record back to 13.1 Ma in the Linxia basin, at the northeast edge of the Tibetan Plateau. By comparing the grain-size distribution of the Linxia basin sediment with known eolian sediments in the region we argue that the 10–70 μm fraction is mostly eolian. This fraction becomes increasingly dominant in the record after 7.4 Ma, with almost all sediments eolian in origin after 6.2 Ma. Given that the 10–70 μm fraction in the Linxia basin are well sorted and have grain-size spectra that are very similar to sediments transported by the Asian winter monsoon, we suggest that the continuous presence of this fraction throughout our record indicates that the Asian winter monsoon has been present in some form since 13.1 Ma. If the assumption that variation in grain-size spectra on the million-year time scale is primarily controlled by the character of eolian input to the basin is valid, the long-term pattern of the eolian fraction reveals two abrupt intensifications of the Asian winter monsoon at 7.4 Ma and 5.3 Ma. These are superimposed on a gradual intensification of the Asian winter monsoon beginning at 8.0–7.4 Ma. We note that the two abrupt intensifications may be related to Arctic ice volume increase, and that the gradual intensification of the Asian winter monsoon after 7.4 Ma is accompanied by central Asia desertification and may therefore be related to increase in the height or extent of the Tibetan Plateau.

Recognition of Printed Arabic Character Using Gray- Scale Matrices

An Optical Character Recognition (OCR) approach for printed Arabic script is presented in this paper, Which is one of the most popular scripts in the world. Development of an OCR system. For Arabic script it is difficult because Arabic characters are distinct and many structurally similar characters exist in the character set. In the proposed approach, the technique can be divided into three major steps. The first step is digitization then do some pre-processing like segmentation to detect the slant of character and correct it .Second, feature extraction , using gray-level matrices. Finally, the K-Nearest-Neighbors is used for classification. This method was tested using 45 patterns for each Arabic character with different fonts (simplified Arabic, tahoma, traditional Arabic), The sample images were divided into 20 training and 25 test images. Images in the test set did not appear in the training sets. This method performs extremely well with recognition rates .90.3%. This is a very good performance. All of this demonstrates that the new method is able to handle printed Arabic character task efficiently. It is a promising technique for recognition printed Arabic character. 1. Introduction Optical character recognition (OCR), deals with the recognition of optically processed character rather magnetically processed ones. In a typical OCR system, input characters are read and digitized by an optical scanner. Each character is then located, segmented and the resulting matrix is fed into a preprocessor. Off-line recognition can de considered the most general case: no special device is required for writing and signal interpretation is independent of signal generation, as in human recognition [6]. The recognition of Arabic character has been an area of great interest for many years, and a number of research papers and reports have already been published in this area. There are several major problems with Arabic character recognition: Arabic characters are distinct and ideographic, many structurally similar character exist in the character set Table (1). Thus, classification criteria are difficult to generate [1 J[3j[6]. The Arabic language has a rich vocabulary. More than 200 million people speak this language as their native speaking, and over 1 billion people use its character set, such as Persian and Urdu, Due to the cursive nature of the script, there are several characteristic that make recognition of Arabic distinct from the recognition of Latin script or Chinese The study of Arabic character recognition has been regarded since 1980s. However, in comparison with the other languages, such as Latin, Chinese and Japanese, there is a little work has been conducted on the automatic recognition of Arabic character [4][5].

KHMER PRINTED CHARACTER RECOGNITION BY USING WAVELET DESCRIPTORS

In Khmer printed characters, same character has various shapes according to the fonts and some characters are very similar in shape. In this paper we try to solve these problems, and propose a method of Khmer printed character recognition by using Wavelet Descriptors. In the recognition, firstly the Khmer printed character images are converted to skeleton forms, then skeletons of Khmer character are converted to temporal domain. The templates are obtained by wavelet coefficients from the character training set. To match the input characters with templates, the character recognition method using deformable wavelet descriptor is adapted by using fixed template and Euclidean distance classifier for matching. The smallest distance is the recognition result of the proposed method. As a result, the deformation can be skipped because it might get low recognition rate of similar characters. The experiment consists of two parts. The first part is to evaluate the overall recognition rate of input characters with three different sizes (22-point, 18-point and 12-point) from 10 different fonts of Khmer printed character. Twenty styles of characters are used as the training set. The results show 92.85, 91.66, and 89.27 percent for 22-point, 18-point, and 12-point respectively. The second part is to specifically evaluate the system, testing with one document that has 21 pages of Khmer printed character with different resolutions from a scanner and facsimile (fax). The document is initially printed with 300 dpi (dots per inch), then scanned with three different resolutions, 600 dpi, 300 dpi and 150 dpi. The document that received from fax machine is scanned by 300 dpi. The results show 92.99, 88.61, and 80.05 percent recognition rate for 300, 150 dpi resolutions, and input from fax respectively.

Combination of statistical and neural classifiers for a high‐accuracy recognition of large character sets

AbstractIn this paper the authors propose a method for high‐accuracy recognition of large character sets using a new combination of a statistical method and neural networks. In their method, a hierarchical structure that has several neural networks arranged in a line after the statistical method is used. First, recognition using a statistical method is performed, and this represents the final result if the top candidate does not belong to a predefined set of similar characters. If it does, then the input character is discriminated in a neural network which designates the top candidate by determining the similar characters. The results are output as final results. The basic idea of this method is the functional division of a statistical method and neural networks, and the use of a neural network as determined by a statistical method. The results of recognizing 3201 character types including JIS‐1 Kanji showed an improvement in the correct recognition rate due to the combined use of a statistical method and neural networks, thereby demonstrating the validity of the authors' approach. © 2005 Wiley Periodicals, Inc. Syst Comp Jpn, 36(9): 97–107, 2005; Published online in Wiley InterScience (www.interscience. wiley.com). DOI 10.1002/scj.20330

A hybrid method for robust car plate character recognition

Image-based car plate recognition is an indispensable part of an intelligent traffic system. The quality of the images taken for car plates, especially for Chinese car plates, however, may sometimes be very poor, due to the operating conditions and distortion because of poor photographical environments. Furthermore, there exist some “similar” characters, such as “8” and “B”, “7” and “T” and so on. They are less distinguishable because of noises and/or distortions. To achieve robust and high recognition performance, in this paper, a two-stage hybrid recognition system combining statistical and structural recognition methods is proposed. Car plate images are skew corrected and normalized before recognition. In the first stage, four statistical sub-classifiers recognize the input character independently, and the recognition results are combined using the Bayes method. If the output of the first stage contains characters that belong to prescribed sets of similarity characters, structure recognition method is used to further classify these character images: they are preprocessed once more, structure features are obtained from them and these structure features are fed into a decision tree classifier. Finally, genetic algorithm is employed to achieve optimum system parameters. Experiments show that our recognition system is very efficient and robust. As part of an intelligent traffic system, the system has been in successful commercial use.

네트워크 침입방지 시스템을 위한 고속 패턴 매칭 가속 시스템

패턴 매칭(Pattern Matching)은 네트워크 침입방지 시스템에서 가장 중요한 부분의 하나며 많은 연산을 필요로 한다. 날로 증가되는 많은 수의 공격 패턴을 다루기 위해, 네트워크 침입방지 시스템에서는 회선 속도로 들어오는 패킷을 처리 할 수 있는 다중 패턴 매칭 방법이 필수적이다. 본 논문에서는 현재 많이 사용되고있는 네트워크 침입방지 및 탐지 시스템인 Snort와 이것의 패턴 매칭 특성을 분석한다. 침입방지 시스템을 위한 패턴 매칭 방법은 다양한 길이를 갖는 많은 수의 패턴과 대소문자 구분 없는 패턴 매칭을 효과적으로 다룰 수 있어야 한다. 또한 여러 개의 입력 문자들을 동시에 처리 할 수 있어야 한다. 본 논문에서 Shift-OR 패턴 매칭 알고리즘에 기반을 둔 다중 패턴 매칭 하드웨어 가속기를 제시하고 여러 가지 가정 하에서 성능 측정을 하였다. 성능 측정에 따르면 제시된 하드웨어 가속기는 현재 Snort에서 사용되는 가장 빠른 소프트웨어 다중 패턴 매칭 보다 80배 이상 빠를 수 있다. Pattern matching is one of critical parts of Network Intrusion Prevention Systems (NIPS) and computationally intensive. To handle a large number of attack signature fattens increasing everyday, a network intrusion prevention system requires a multi pattern matching method that can meet the line speed of packet transfer. In this paper, we analyze Snort, a widely used open source network intrusion prevention/detection system, and its pattern matching characteristics. A multi pattern matching method for NIPS should efficiently handle a large number of patterns with a wide range of pattern lengths and case insensitive patterns matches. It should also be able to process multiple input characters in parallel. We propose a multi pattern matching hardware accelerator based on Shift-OR pattern matching algorithm. We evaluate the performance of the pattern matching accelerator under various assumptions. The performance evaluation shows that the pattern matching accelerator can be more than 80 times faster than the fastest software multi-pattern matching method used in Snort.

Speech synthesis with prosodic model data and accent type

A speech synthesizing method includes determining the accent type of the input character string, selecting the prosodic model data from a prosody dictionary for storing typical ones of the prosodic models representing the prosodic information for the character strings in a word dictionary, based on the input character string and the accent type, transforming the prosodic information of the prosodic model when the character string of the selected prosodic model is not coincident with the input character string, selecting the waveform data corresponding to each character of the input character string from a waveform dictionary, based on the prosodic model data after transformation, and connecting the selected waveform data with each other. Therefore, a difference between an input character string and a character string stored in a dictionary is absorbed, then it is possible to synthesize a natural voice.

Development of Character Input Interface using Laplacian EMG with Wireless Active Electrode

Development of Character Input Interface using Laplacian EMG with Wireless Active Electrode

Input of Japanese Characters by Recognizing the Number of Fingers

Many recent studies centered on recognizing human gestures using images for man-machine interfaces do not deal with information on Japanese or other characters. We propose inputting Japanese characters by recognizing the number of fingers of one hand. Recognized numbers are converted to characters using the “pocket-bell” rule. The number is recognized by image processing. Range images are used as image information to implement the method. We also discuss how to control recognition timing and canceling input data. Experimental results using a range image sensor show the effectiveness of the proposed methods.

Real‐time recognition of handwritten math formulas

AbstractThis paper proposes a method of realizing a handwritten mathematical formula input system that works in real time. In the handwritten character input, the data is input generally for each stroke (segment). The proposed method is based on this property. The mathematical formula is recognized on the basis of the result of recognition of the individual input strokes and their positional relations. Then the LaTeX source code is generated. In this paper, mathematical symbols are considered as characters, and are integrated into character recognition. More precisely, each time a stroke is input, it is recognized as a single‐stroke character. The crossing with the already input characters is examined, and the character is extracted so that the likelihood of forming character is maximized. Based on the positional relations among the extracted characters, the structure of the mathematical formula, such as superscripts/subscripts and fractions, is recognized. The mathematical structures that can be recognized by the proposed method are the structures obtained by combining five different structures, namely, superscript/subscript, root, overline, underline, and fraction. The recognition is not affected by the order of input. The proposed method is applied to various mathematical formulas, and it is seen that the proposed system works adequately as an input environment for real‐time processing. © 2004 Wiley Periodicals, Inc. Electron Comm Jpn Pt 3, 87(8): 66–81, 2004; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/ecjc.20086

745 頭の傾きと呼吸気を利用した文字入力支援装置の開発(支援機器, OS-22 福祉工学)

This paper describes support-equipment of operating a personal computer for users who have an obstacle on the regions of upper limb. The user wears a head set device with an angle sensor, and holds a plastic pipe connected to a pressure sensor in his or her mouth. Tilting his or her head and breathing are used for a mouse cursor operation and characters input. The voluntary tilt angle range and breath strength are memorized to the controller beforehand, so that operations can be performed without fatigue considering user's body situations.

Development of Character Input System using Facial Muscle Signals

A person does communication between each other using language. But, In the case of disabled person, he/she could not transfer own idea to others by using the writing or gesture. We embodied communication system using the facial muscle signals so that disabled person can do communication. After feature extraction from the facial muscle signals, it is converted to the control signal, and then disabled person could transfer his/her intention by select characters.

AN APPROACH TO NATURAL STROKE EXTRACTION FOR OFF-LINE LOOSELY-CONSTRAINED HANDWRITTEN CHINESE CHARACTERS

This paper proposes a new approach to extracting natural strokes from the skeletons of loosely-constrained, off-line handwritten Chinese characters. It admits the output substrokes from a previously proposed fuzzy substroke extractor as its inputs. By identifying a number of expected ambiguities which include mutual similarities, unstable touches and joint/cross distortions, fuzzy stroke models are constructed and a "hit-all" fuzzy stroke matching strategy is pursued. Fuzzy partitioning technique is used to generate a ranked list of consistent stroke sets from the set of fuzzy strokes being identified. With this approach, a maximum of 20 distinct natural stroke classes can be extracted from each input character, together with an estimate on the actual count of strokes which compose the character. Our system offers a number of performance tuning capabilities such as the computation of the fuzzy scores of each extracted stroke, the adjustment on the fuzzy stroke model parameters, and the potential of incorporating one's personal writing styles into our methodology.

다중 신경망을 이용한 인식단위 결합 기반의 인쇄체 문자인식

본 논문에서는 다중 신경망을 이용한 인식단위 결합 기반의 인쇄체 문자인식 방법을 제안한다. 입력 문자영상은 한글 문자 형식 6가지와 한글 이외의 기타 문자 형식의 전체 7가지 형식으로 분류되어 인식된다. 한글 문자는 2단계의 MLP 신경망 인식기에 의해 인식된다. 첫째 단계에서는 한글 문자를 자소의 조합 형태에 따라 2개 또는 3개의 인식단위로 나누고, 각 인식단위에서 추출된 방향각도 특징 벡터를 입력으로 하는 MLP 신경망으로 1차 인식한다. 둘째 단계에서는 첫째 단계의 인식단위별 MLP 신경망 인식기의 인식양상 특징을 추출하고 다른 MLP 신경망에 입력하여 최종 한글 문자인식을 한다. 한글 이외의 기타 문자의 인식을 위해서는 단일 MLP 신경망을 사용한다. 인식 실험에서는 실제 우편물 50,000통 영상으로부터 추출한 문자영상 데이터베이스를 이용하였는데, 실험 결과 본 논문에서 제안한 방법이 매우 우수함을 알 수 있었다. In this Paper. we propose a recognition method of machine printed characters based on the combination of recognition units using multiple neural networks. In our recognition method, the input character is classified into one of 7 character types among which the first 6 types are for Hangul character and the last type is for non-Hangul characters. Hangul characters are recognized by several MLP (multilayer perceptron) neural networks through two stages. In the first stage, we divide Hangul character image into two or three recognition units (HRU : Hangul recognition unit) according to the combination fashion of graphemes. Each recognition unit composed of one or two graphemes is recognized by an MLP neural network with an input feature vector of pixel direction angles. In the second stage, the recognition aspect features of the HRU MLP recognizers in the first stage are extracted and forwarded to a subsequent MLP by which final recognition result is obtained. For the recognition of non-Hangul characters, a single MLP is employed. The recognition experiments had been performed on the character image database collected from 50,000 real letter envelope images. The experimental results have demonstrated the superiority of the proposed method.

Fast and compact updating algorithms of a double-array structure

In many information retrieval applications, it is necessary to be able to adopt a trie search for looking at the input character by character. As a fast and compact data structure for a trie, a double-array is presented. However, the insertion time is not faster than other dynamic retrieval methods because the double-array is a semi-static retrieval method that cannot treat high frequent updating. Further, the space efficiency of the double-array degrades with the number of deletions because it keeps empty elements produced by deletion. This paper presents a fast insertion algorithm by linking empty elements to find inserting positions quickly and a compression algorithm by reallocating empty elements for each deletion. From the simulation results for 100 thousands keys, it turned out that the insertion time and the space efficiency are achieved.