Hideaki YAMAGATA Hirobumi NISHIDA Toshihiro SUZUKI Michiyoshi TACHIKAWA Yu NAKAJIMA Gen SATO
Handwritten character recognition has been increasing its importance and has been expanding its application areas such as office automation, postal service automation, automatic data entry to computers, etc. It is challenging to develop a handwritten character recognition system with high processing speed, high performance, and high portability, because there is a trade-off among them. In current technology, it is difficult to attain high performance and high processing speed at the same time with single algorithms, and therefore, we need to find an efficient way of combination of multiple algorithms. We present an engineering solution to this problem. The system is based on multi-stage strategy as a whole: The first stage is a simple, fast, and reliable recognition algorithm with low substitution-error rate, and data of high quality are recognized in this stage, whereas sloppily written or degraded data are rejected and sent out to the second stage. The second stage is composed of a sophisticated structural pattern classifier and a pattern matching classifier, and these two complementary algorithms run in parallel (multiple expert approach). We demonstrate the performance of the completed system by experiments using real data.
In this letter, we propose an adaptive multiuser receiver using a Hopfield network for code-division multiple-access communications and its performance is compared with that of the other types of multiuser receiver via computer simulation. The proposed adaptive receiver estimates both the signal amplitudes and spreading sequences for all the users using training data.
In ths letter, we suggest a collision resolution algorithm when the packet length is random, and analyze its throughput and delay performance. Here, three different packet length distributions and two feedback schemes (ternary and binary success/failure feedback) are considered.
Masataka OHTSUKA Yoshihiko KONISHI Makoto MATSUNAGA Takashi KATAGI
In this paper, authors propose a linear array antenna using two bifilar helical antenna elements placed along the helix axis to reduce beam direction movement according to frequency change. The beam direction movement of this proposed array antenna is smaller than that of a conventional bifilar helical antenna. Also, the gain of this proposed array antenna is higher than that of the conventional helical antenna for a cross point angle of radiation patterns at the different transmit and receive(Tx and Rx) frequencies. The conventional helical antenna is suitable for vehicle antennas in mobile satellite communication systems such as the MSAT system because it owns circularly polarized omni-directional radiation pattern and its thin pole form. However, this antenna has a disadvantage that the beam direction in an elevation plane moves according to frequency change. In the proposed array antenna, the beam direction movement is about 9 smaller than that of the conventional bifilar helical antenna on condition that antenna total length is 4.83 λ0, antenna diameter is 0.12 λ0, and frequency change is from 0.957f0 to 1.043f0(f0 is center frequency and λ0 is free space wavelength at f0). Also, the Tx and Rx gains of this proposed array antenna at the cross point angle between Tx and Rx beams are about 2 dB higher than that of the conventional bifilar helical antenna on the same condition.
Hiroshi KONDO Suharno AGUS Mariko MOROKUMA
One approach for image edge sharpening which includes a phase-only synthesis (POS) is presented. The technique presented here is the generalized version of the traditional Laplacian image enhancement. The utilizing of an internally dividing point between the POS and the Laplacian enhancement image makes this approach more flexible, more effective.
Yoshifumi SUZUKI Tadashi SHIRATO
This paper proposes a new digitized group modulator for radio base station transmitters of multi-carrier TDMA. This group modulator can flexibly set carrier spacing and features a simple construction as a result of employing the Simple Fractional Sampling technique. A group modulator LSI was designed and built using 0.5-µm BiCMOS technology, and a π/4-shifted QPSK group modulator was constructed using this LSI. Experiments confirm that the modulator simultaneously generates multiple carriers in a wide bandwidth without the need for precise adjustment and there is little difference between each of the carriers in terms of BER performance. Moreover, experiments confirm that the group modulator's burst-output (frequency hopping) performance is excellent.
For similarity methods to work well, the image must be blurred before being input. However, the relationship between the blurring operation and the similarity is not fully understood. To solve the problem of this relationship, in this paper, the effect of blurring is investigated by expressing figure f(x) in the form of the sum of higher derivatives of f (x,σ), and then a simple similarity between figures was mathematically formulated in terms of the relation between visual patterns. By modifying this formulation, we propose pluralized simple similarity to increase the allowance in different view of multiple similarity. The similarity maintains higher allowance without any discernible loss of distinguishing power. We verify the effectiveness of the pluralized simple similarity throughout some experiments.
Caiming ZHANG Takeshi AGUI Hiroshi NAGAHASHI
A new global method for constructing a C2 piecewise quartic polynomial curve is presented. The coefficient matrix of equations which must be solved to construct the curve is tridiagonal. The joining points of adjacent curve segments are the given data points. The constructed curve reproduces exactly a polynomial of degree four or less. The results of experiments to test the efficiency of the new method are also shown.
Yukio KAMATANI Yoshihiro OHBA Yoshimitsu SHIMOJO Koutarou ISE Masahiko MOTOYAMA Toshitada SAITO
Asynchronous Transfer Mode (ATM) is a promised bearer transmission service for high speed multimedia LAN. Recently, high speed multimedia ATM LAN products have been available. Therefore, in order to interconnect them, the multimedia backbone LAN, which has the expandable high throughput over 10Gbps, supporting multicast, multi-QoS, and many interfaces including 622 Mbps, will be widely required. In this paper, the VLSI oriented input and output buffered switch architecture is proposed as the hardware architecture for multimedia backbone switch node. This paper describes that the chip set consisting of four VLSIs, that is, the switch element, the switch access, the distributor/arbiter, and the multiplexer/demultiplexer, can realize the backbone switch core, and the main specifications required to each VLSI are derived.
Kanad KEENI Hiroshi SHIMODAIRA Tetsuro NISHINO Yasuo TAN
Devanagari is the most widely used script in India. Here, a method is introduced for recognizing Devanagari characters using Neural network. The proposed method reduces the number of output unit necessary for a conventional neural network where the classification is based on a winner take all basis. An automatic coding procedure for representing the output layer of the network and a different method for the final classification is also proposed. Along with the automatic coding procedure, a heuristic method for representing the output units by exploiting the structural information of Devanagari character is also demonstrated. Besides, it has been shown by random representation of the output layer that the representation effects the generalization/performance of the network. The proposed automatic representation gave the recognition rate of 98.09% for 44 categories.
It is well known that the Hopfield Model (HM) for neural networks to solve the TSP suffers from three major drawbacks: (D1) it can converge to non-optimal local minimum solutions; (D2) it can also converge to non-feasible solutions; (D3) results are very sensitive to the careful tuning of its parameters. A number of methods have been proposed to overcome (D1) well. In contrast, work on (D2) and (D3) has not been sufficient; techniques have not been generalized to larger classes of optimization problems with constraint including the TSP. We first construct Extended HMs (E-HMs) that overcome both (D2) and (D3). The extension of the E-HM lies in the addition of a synapse dynamical system cooperated with the corrent HM unit dynamical system. It is this synapse dynamical system that makes the TSP constraint hold at any final states for whatever choices of the HM parameters and an initial state. We then generalize the E-HM further into a network that can solve a larger class of continuous optimization problems with a constraint equation where both of the objective function and the constraint function are non-negative and continuously differentiable.
Fernando Gil V. RESENDE Jr. Keiichi TOKUDA Mineo KANEKO
A new adaptive AR spectral estimation method is proposed. While conventional least-squares methods use a single windowing function to analyze the linear prediction error, the proposed method uses a different window for each frequency band of the linear prediction error to define a cost function to be meinemized. With this approach, since time and frequency resolutions can be traded off throughout the frequency spectrum, an improvement on the precision of the estimates is achieved. In this paper, a wavelet-like time-frequency resolution grid is used so that low-frequency components of the linear prediction error are analyzed through long windows and high-frequency components are analyzed through short ones. To solve the optimization problem for the new cost function, special properties of the correlation matrix are used to derive an RLS algorithm on the order of M2, where M is the number of parameters of the AR model. Computer simulations comparing the performance of conventional RLS and the proposed methods are shown. In particular, it can be observed that the wavelet-based spectral estimation method gives fine frequency resolution at low frequencies and sharp time resolution at high frequencies, while with conventional methods it is possible to obtain only one of these characteristics.
Yasuhiro SUGIMOTO Takaaki TSUJI
This paper examines the feasibility of a high frequency (moro than 1 GHz) ring-oscillator-type CMOS VCO, able to maintain a good linearity between the oscillator output frequency and control voltage, while preserving low voltage and low power operation capabilities. A CMOS VCO circuit, with a newly developed corrent-controlled delay cell and an architecture combining the transitions of each delay cell output, with high-frequency operation, was designed and simulated using the CMOS 0.6 µm device paramenters. We analyzed the generation of unnecessary harmonics and sub-harmonics when a delay cell's propagation delay time varied. The simulation indicated that a CMOS VCO with a frequency range of 200 MHz to 1.4 GHz, a power dissipation of 8.5 mW at 900 MHz from a 3 V power supply, and an operation voltage of 1 V to 3 V can be implemented on a chip.
Toru WAKAHARA Akira SUZUKI Naoki NAKAJIMA Sueharu MIYAHARA Kazumi ODAKA
This paper describes an on-line Kanji character recognition method that solves the one-to-one stroke correspondence problem with both the stroke-number and stroke-order variations common in cursive Japanese handwriting. We propose two kinds of complementary algorithms: one dissolves excessive mapping and the other dissolves deficient mapping. Their joint use realizes stable optimal stroke correspondence without combinatorial explosion. Also, three kinds of inter-stroke distances are devised to deal with stroke concatenation or splitting and heavy shape distortion. These new ideas greatly improve the stroke matching ability of the selective stroke linkage method reported earlier by the authors. In experiments, only a single reference pattern for each of 2,980 Kanji character categories is generated by using training data composed of 120 patterns written carefully with the correct stroke-number and stroke-order. Recognition tests are made using the training data and two kinds of test data in the square style and in the cursive style written by 36 different people; recognition rates of 99.5%, 97.6%, and 94.1% are obtained, respectively. Moreover, comparative results obtained by the current OCR technique as applied to bitmap patterns of on-line character data are presented. Finally, future work for enhancing the stroke matching approach to cursive Kanji character recognition is discussed.
Peng ZHAO Atsusi HIGASHI Yukio SATO
This paper deals with on-line signature verification. A signature is obtained as a sequence of x, y-coordinates of pen-tip movement and writing pressure. The features of a signature are derived from the coordinates and the writing pressure and are decomposed into two principal features, shape and motion, using the DP-matching technique. We found that each point of a signature varies each time to some degree. However, the degrees of local variations subject to points, as some points are relatively stable and do not vary much while some of them are not. In this paper, we propose to incorporate weighted local variations based on the stability of each point so as to evaluate the difference of two signatures locally as well as globally. The dissimilarity measures are presented with respect to the corresponding features and are combined into one for efficient verification. In addition to the x, y-coordinates, the writing pressure is also considered to be part of shape. Experiments were carried out with a database which consists of 300 genuine signatures and 300 forgeries collected from 10 subjects. The effectiveness of incorporating the weighted local variation is shown by the experimental results. It contributes to an average increase in the correct verification rate as the correct verification rate increased 1.0% and was found to be 98.7%.
Takehiko OGAWA Keisuke KAMEYAMA Roman KUC Yukio KOSUGI
A new neural network for locating a source by integrating data from a number of sensors is considered. The network gives a solution for inverse problems using a back-propagation algorithm with the architecture to get the solution in the inter-layer weights in a coded form Three different physical quantities are applied to the network, since the scheme has three independent ports; an input port, a tutorial port and an answer port. Our architecture is useful to estimate z" in the problem whose structure is y=f(x,z) where y is the observed data, x is the sensor position and z is the source location. The network integrates the information obtained from a number of sensors and estimates the location of the source. We apply the network to two problems of location estimation: the localization of the active nerves from their evoked potential waveforms and the localization of objects from their echoes using an active sonar system.
Hidetoshi YOKOO Masaharu TAKAHASHI
This paper proposes a new lossless data compression method, which utilizes a context sorting algorithm. Every symbol in the data can be predicted by taking its immediately preceding characters, or context, into account. The context sorting algorithm sorts a set of all the previous contexts to find the most similar context to the current one. It then predicts the next symbol by sorting previous symbol-context pairs in an order of context similarity. The codeword for the next symbol represents the rank of the symbol in this sorted sequence. The compression performance is evaluated both analytically and empirically. Although the proposed method operates character by character, with no probability distribution used to make a prediction, it has comparable compression performance to the best known data compression utilities.
This paper is described on the realization of simulated inductance cercuit with parallel negative conductance and its application for an oscillator. The design's condition for realizing the circuit needs stability, narrow expance of elements, larger dynamic-range and lower sensitivity. A new floating simulated inductance circuit with parallel nagative conductance with two operational amplifiers, four resistors, and four capacitors is created by using the design's algorithm. And the elements sensitivity of the simulated circuit is superior to that of the conventional circuits. By experimenting with a resonance circuit, the author tested the sinusoidal oscillator's circuit of a parallel -GLC as an application in order to confirm the operation of the simulated inductance circuit with parallel negative conductance.
Yoshitada IYAMA Noriharu SUEMATSU Tomonori SHIGEMATSU Takao MORIWAKI Tatsuhiko IKEDA
A simplified equivalent circuit, which is useful in L-band, of switching MOSFET is presented. The MOSFET model accounts for the relatively low resistivity of Si substrate. By using this circuits, the relationship between the MOSFET equivalent circuit parameters and a series-shunt FET connected SPDT switch characteristics has been revealed. In order to evaluate the relationship mentioned above, enhancement type NMOSFETs and a SPDT switch with the FETs are fabricated. The MOSFET equivalent circuit parameters at L-band were extracted from measured small-signal S-parameters of the FETs. The measured switch characteristics are fairly good agreement with the simulated results which has been accomplished by using the MOSFET model. This good agreements shows the effectiveness of the MOSFET model which is presented here.
Toshiyuki YOSHIDA Todor COOKLEV Akinori NISHIHARA Nobuo FUJII
This paper proposes a design technique for 3-D non-separable QMF banks with Face-Centered Cubic Sampling (FCCS) and Body-Centered Cubic Sampling (BCCS). In the proposed technique, 2-D McClellan transformation is applied to a suitably designed 2-D prototype QMF to obtain 3-D QMFs. The design examples given in this paper demonstrate advantages of the proposed method.