This paper presents a survey of elastic matching (EM) techniques employed in handwritten character recognition. EM is often called deformable template, flexible matching, or nonlinear template matching, and defined as the optimization problem of two-dimensional warping (2DW) which specifies the pixel-to-pixel correspondence between two subjected character image patterns. The pattern distance evaluated under optimized 2DW is invariant to a certain range of geometric deformations. Thus, by using the EM distance as a discriminant function, recognition systems robust to the deformations of handwritten characters can be realized. In this paper, EM techniques are classified according to the type of 2DW and the properties of each class are outlined. Several topics around EM, such as the category-dependent deformation tendency of handwritten characters, are also discussed.

The performance of integrated segmentation and recognition of handwritten numeral strings relies on the classification accuracy and the non-character resistance of the underlying character classifier, which is variable depending on the techniques of pattern normalization, feature extraction, and classifier structure. In this paper, we evaluate the effects of 12 normalization functions and four selected feature types on numeral string recognition. Slant correction (deslant) is combined with the normalization functions and features so as to create 96 feature vectors, which are classified using two classifier structures. In experiments on numeral string images of the NIST Special Database 19, the classifiers have yielded very high string recognition accuracies. We show the superiority of moment normalization with adaptive aspect ratio mapping and the gradient direction feature, and observed that slant correction is beneficial to string recognition when combined with good normalization methods.

This paper proposes a "structuring search space" (SSS) method aimed to accelerate recognition of large character sets. We divide the feature space of character categories into smaller clusters and derive the centroid of each cluster as a pivot. Given an input pattern, it is compared with all the pivots and only a limited number of clusters whose pivots have higher similarity (or smaller distance) to the input pattern are searched in, thus accelerating the recognition speed. This is based on the assumption that the search space is a distance space. We also consider two ways of candidate selection and finally combine them the method has been applied to a practical off-line Japanese character recognizer with the result that the coarse classification time is reduced to 56% and the whole recognition time is reduced to 52% while keeping its recognition rate as the original.

This paper incorporates statistical language models into an on-line handwriting recognition system for devices with limited memory and computational resources. The objective is to minimize the error recognition rate by taking into account the sentence context to disambiguate poorly written texts. Probabilistic word n-grams have been first investigated, then to fight the curse of dimensionality problem induced by such an approach and to decrease significantly the size of the language model an extension to class-based n-grams has been achieved. In the latter case, the classes result either from a syntactic criterion or a contextual criteria. Finally, a composite model is proposed; it combines both previous kinds of classes and exhibits superior performances compared with the word n-grams model. We report on many experiments involving different European languages (English, French, and Italian), they are related either to language model evaluation based on the classical perplexity measurement on test text corpora but also on the evolution of the word error rate on test handwritten databases. These experiments show that the proposed approach significantly improves on state-of-the-art n-gram models, and that its integration into an on-line handwriting recognition system demonstrates a substantial performance improvement.

This paper presents a model and its effect for on-line handwritten Japanese text recognition free from line-direction constraint and writing format constraint such as character writing boxes or ruled lines. The model evaluates the likelihood composed of character segmentation, character recognition, character pattern structure and context. The likelihood of character pattern structure considers the plausible height, width and inner gaps within a character pattern that appear in Chinese characters composed of multiple radicals (subpatterns). The recognition system incorporating this model separates freely written text into text line elements, estimates the average character size of each element, hypothetically segments it into characters using geometric features, applies character recognition to segmented patterns and employs the model to search the text interpretation that maximizes likelihood as Japanese text. We show the effectiveness of the model through recognition experiments and clarify how the newly modeled factors in the likelihood affect the overall recognition rate.

This paper describes an on-line handwritten Japanese text recognition system that is liberated from constraints on line direction and character orientation. The recognition system first separates freely written text into text line elements, second estimates the line direction and character orientation using the time sequence information of pen-tip coordinates, third hypothetically segment it into characters using geometric features and apply character recognition. The final step is to select the most plausible interpretation by evaluating the likelihood composed of character segmentation, character recognition, character pattern structure and context. The method can cope with a mixture of vertical, horizontal and skewed text lines with arbitrary character orientations. It is expected useful for tablet PC's, interactive electronic whiteboards and so on.

A new method for logical structure analysis of document images is proposed in this paper as the basis for a document reader which can extract logical information from various printed documents. The proposed system consists of five basic modules: text line classification, object recognition, object segmentation, object grouping, and object modification. Emergent computation, which is a key concept of artificial life, is adopted for the cooperative interaction among modules in the system in order to achieve effective and flexible behavior of the whole system. It has three principal advantages over other methods: adaptive system configuration for various and complex logical structures, robust document analysis tolerant of erroneous feature detection, and feedback of high-level logical information to the low-level physical process for accurate analysis. Experimental results obtained for 150 documents show that the method is adaptable, robust, and effective for various document structures.

Question answering (QA) is the task of retrieving an answer in response to a question by analyzing documents. Although most of the efforts in developing QA systems are devoted to dealing with electronic text, we consider it is also necessary to develop systems for document images. In this paper, we propose a method of document image retrieval for such QA systems. Since the task is not to retrieve all relevant documents but to find the answer somewhere in documents, retrieval should be precision oriented. The main contribution of this paper is to propose a method of improving precision of document image retrieval by taking into account the co-occurrence of successive terms in a question. The indexing scheme is based on two-dimensional distributions of terms and the weight of co-occurrence is measured by calculating the density distributions of terms. The proposed method was tested by using 1253 pages of documents about the major league baseball with 20 questions and found that it is superior to the baseline method proposed by the authors.

Data clustering is a technique for grouping similar data items together for convenient understanding. Conventional data clustering methods, including agglomerative hierarchical clustering and partitional clustering algorithms, frequently perform unsatisfactorily for large text collections, since the computation complexities of the conventional data clustering methods increase very quickly with the number of data items. Poor clustering results degrade intelligent applications such as event tracking and information extraction. This paper presents an unsupervised document clustering method which identifies topic keyword clusters of the text corpus. The proposed method adopts a multi-stage process. First, an aggressive data cleaning approach is employed to reduce the noise in the free text and further identify the topic keywords in the documents. All extracted keywords are then grouped into topic keyword clusters using the k-nearest neighbor approach and the keyword clustering technique. Finally, all documents in the corpus are clustered based on the topic keyword clusters. The proposed method is assessed against conventional data clustering methods on a web news corpus. The experimental results show that the proposed method is an efficient and effective clustering approach.

This paper presents the design of new fully differential CMOS class A and class AB current-mode transmitters for multi-Gbps serial links. A high multiplexing speed is achieved by multiplexing at low-impedance nodes and inductive shunt peaking with active inductors. The fully complementary operation of the multiplexers and the fully differential configuration of the transmitters minimizes the effect of common-mode disturbances and that of EMI from channels to neighboring devices. Large output current swing is obtained by making use of differential current amplifiers and the differential rail-to-rail configuration. The constant current drawn from the supply voltage minimizes the noise injected into the substrate. The transmitters have been implemented in TSMC's 1.8 V 0.18 µm CMOS technology and analyzed using Spectre from Cadence Design Systems with BSIM3V device models. Simulation results confirm that the proposed transmitters are capable of transmitting data at 10 Gbps.

Faults in computer systems can occur due to a variety of reasons. These include internal effects such as coupling and external effects such as alpha particles. As we move towards smaller manufacturing technologies, the probability of errors for a single transistor is likely to increase. Even if this probability remains the same, the probability of a fault in a processor will increase linearly with the boost in the number of transistors per chip. In many systems, an error has a binary effect, i.e., the output is either correct or erroneous. However, networking systems exhibit different properties. For example, although a portion of the code behaves incorrectly due to a fault, the application can still work correctly. Therefore, measuring the effects of faults on the network processor applications require new measurement metrics to be developed. Particularly, hardware faults need to be measured in the context of their effect on the application behavior. In this paper, we highlight essential application properties and data structures that can be used to measure the error behavior of network processors. Using these metrics, we study the error behavior of seven representative networking applications under different cache access fault probabilities. With this study, we hope to bridge the gap between the circuit-level phenomena and their impact on the application behavior.

JPEG2000 image compression standard is designed to cater the needs of a large span of applications including numerous consumer products. However, its use is restricted due to the high hardware cost involved in its implementation. Bit Plane Coder (BPC) is the main resource intensive component of JPEG2000. Its throughput plays a key role in deciding the overall throughput of a JPEG2000 encoder. In this paper we present the algorithm and parallel pipelined VLSI architecture for BPC which processes a complete stripe-column concurrently during every pass. The hardware requirements and the critical path delay of the proposed technique are compared with the existing solutions. The experimental results show that the proposed architecture has 2.6 times greater throughput than existing architectures, with a comparatively small increase in hardware cost.

In recent years, there has been an increased focus on the mechanics of information transmission in spiking neural networks. Especially the Noise Shaping properties of these networks and their similarity to Delta-Sigma Modulators has received a lot of attention. However, very little of the research done in this area has focused on the effect the weights in these networks have on the Noise Shaping properties and on post-processing of the network output signal. This paper concerns itself with the various modes of network operation and beneficial as well as detrimental effects which the systematic generation of network weights can effect. Also, a method for post-processing of the spiking output signal is introduced, bringing the output signal more in line with conventional Delta-Sigma Modulators. Relevancy of this research to industrial application of neural nets as building blocks of oversampled A/D converters is shown. Also, further points of contention are listed, which must be thoroughly researched to add to the above mentioned applicability of spiking neural nets.

Information transmission among biological neurons is carried out by a complex series of spike signals. The input inter-spike arrival times at a neuron are believed to carry information which the neurons utilize to carry out a task. In this paper, a new scheme which utilizes the input inter-spike intervals (ISI) for decoding an input spike train is proposed. A spike train consists of a sequence on input spikes with various inter-spike times. This decoding scheme can also be used for neurons which have multiple synaptic inputs but for which each synapse receives a single spike within one input time window. The ISI decoding neural network requires only a few neurons. Example applications show the usefulness of the decoding scheme.

The application of neural networks to the state-feedback guaranteed cost control problem of discrete-time system that has uncertainty in both state and input matrices is investigated. Based on the Linear Matrix Inequality (LMI) design, a class of a state feedback controller is newly established, and sufficient conditions for the existence of guaranteed cost controller are derived. The novel contribution is that the neurocontroller is substituted for the additive gain perturbations. It is newly shown that although the neurocontroller is included in the discrete-time uncertain system, the robust stability for the closed-loop system and the reduction of the cost are attained.

This paper deals with minimum spanning tree problems where each edge weight is a fuzzy random variable. In order to consider the imprecise nature of the decision maker's judgment, a fuzzy goal for the objective function is introduced. A novel decision making model is constructed based on possibility theory and on a stochastic programming model. It is shown that the problem including both randomness and fuzziness is reduced to a deterministic equivalent problem. Finally, a polynomial-time algorithm is provided to solve the problem.

A novel application of fuzzy-neuro approach to protection of double circuit transmission line is demonstrated in this paper. Different system faults on a protected transmission line should be detected and classified rapidly and correctly. Using the proposed approach, fault detection, classification and faulted phase selection could be achieved within a quarter of cycle. Results of performance studies show that the proposed fuzzy-neuro-based module can improve the performance of conventional fault selection algorithms.

This paper describes a distributed video transcoding system that can simultaneously transcode an MPEG-2 video file into various video coding formats with different rates. The transcoder divides the MPEG-2 file into small segments along the time axis and transcodes them in parallel. Efficient video segment handling methods are proposed that minimize the inter-processor communication overhead and eliminate temporal discontinuities from the re-encoded video. We investigate how segment transcoding should be distributed to obtain the shortest total transcoding time. Experimental results show that implementing distributed transcoding on 10 PCs can decrease the total transcoding time by a factor of about 7 for single transcoding and by a factor of 9.5 for simultaneous three kinds of transcoding rates.

R-trees have been traditionally optimized for I/O performance with disk pages as tree nodes. Recently, researchers have proposed cache-conscious variations of R-trees optimized for CPU cache performance in main memory environments, where the node size is several cache lines wide and more entries are packed in a node by compressing MBR keys. However, because there is a big difference between the node sizes of two types of R-trees, disk-optimized R-trees show poor cache performance while cache-optimized R-trees exhibit poor disk performance. In this paper, we propose a cache and disk optimized R-tree, called PR-tree (Prefetching R-tree). For cache performance, the node size of the PR-tree is wider than a cache line, and the prefetch instruction is used to reduce the number of cache misses. For I/O performance, the nodes of the PR-tree are fitted into one disk page. We represent the detailed analysis of cache misses for range queries, and enumerate all the reasonable in-page leaf and nonleaf node sizes, and heights of in-page trees to figure out tree parameters for the best cache and I/O performance. The PR-tree that we propose achieves better cache performance than the disk-optimized R-tree: a factor of 3.5-15.1 improvement for one-by-one insertions, 6.5-15.1 improvement for deletions, 1.3-1.9 improvement for range queries, and 2.7-9.7 improvement for k-nearest neighbor queries. All experimental results do not show notable declines of I/O performance.

This paper proposes two power-constrained test synthesis schemes and scheduling algorithms, under non-scan BIST, for RTL data paths. The first scheme uses boundary non-scan BIST, and can achieve low hardware overheads. The second scheme uses generic non-scan BIST, and can offer some tradeoffs between hardware overhead, test application time and power dissipation. A designer can easily select an appropriate design parameter based on the desired tradeoff. Experimental results confirm the good performance and practicality of our new approaches.

A distributed network-oriented Intrusion Detection System (IDS) is a mechanism which detects misuse accesses to an intra-network by distributed IDSs on the network with decomposed attack scenarios. However, there are only ad hoc algorithms for determining a deployment of distributed IDSs and a partition of the attack scenarios. In this paper, we formally define this problem as the IDS partition deployment problem and design an efficient algorithm for a simplified version of the problem by graph theoretical techniques.

Although the Digital Rights Management (DRM) systems have been rapidly developed to protect copyrights, they have not considered user privacy because they regard this as an unnecessary element in achieving their goals. However, the protection of user privacy becomes one of the most important issues in DRM systems as the number of people who suffer from accidents caused by the infringement of individual information dramatically increases. This paper suggests a license management protocol which is a more powerful protocol to protect individual information in DRM. To protect the exposure of information of user identification, the proposed protocol uses alias like a TID and a token instead of the identity of content users. Due to using alias, this protocol can guarantee the anonymity of content users. Also, it can prevent the leakage of individual information through encryption of usage information. In this way, it can protect the privacy of content users.

We present a model of quantization noise in block-coded videos with some assumptions in wavelet domain and propose a postprocessing method to reduce the quantization noise based on the model. A frame of video sequences is considered as a set of one-dimensional (1-D) horizontal and vertical signals. The quantization noise is considered as the sum of the blocking noise and the remainder noise. We model the blocking noise as an impulse or that along with a dispersed impulse at each block boundary in the wavelet domain. The validity of the blocking noise model is investigated. We also model the remainder noise as white Gaussian noise at non-edge pixels in the wavelet domain. Whether the model accommodates well to the remainder noise or not is also examined. The blocking noise is reduced by subtracting a profile, whose strength is adaptively estimated, at each block boundary from the coded signal. The remainder noise then is reduced by a soft-thresholding. We also propose a fast algorithm for the proposed method by approximating coefficients of shape profiles used in blocking noise reduction and inverse wavelet transform (WT) filters used in remainder noise reduction. The performance is evaluated for QCIF video sequences coded by H.263 TMN5 with quantization parameter (QP) in the range of 5-25 and is compared to that of the MPEG-4 verification model (VM) post-filter. Experimental results show that the proposed method yields not only PSNR improvement of maximum 0.5 dB over the VM post-filter but also subjective quality nearly free of the blocking artifact and edge blur.

This paper presents a new algorithm for efficiently detecting silhouette voxels in volume objects. The high performance of the algorithm is partly due to its ability to exclude all the gradient vectors not associated with silhouettes from further consideration. A judicious re-arrangement of the voxels enhances its efficiency. We have studied its performance through computer simulations. The results indicate a manifold improvement over conventional algorithms. A parallel version of the algorithm has also been described in the paper. Its performance is quite understandably impressive.

General exercise approaches are not convenient for some people in undertaking appropriate exercise due to the limited variety of present programs at existing exercise machines. Moreover, continuous support by one sports doctor is only available for a limited number of users. In this paper, therefore, we propose an Internet-based technical framework, which is designed on multi-tiered client/server architecture, for integrating and easily upgrading exercise programs. By applying the technical framework, a cycle ergometer health promotion system was developed for providing personally fitted. We also presented some facilities to assist sports doctors in quickly designing and remotely improving individual exercise protocols against cycle ergometer exercise based on a history database. Then we evaluated the Internet-based cycle ergometer system during two months of feasibility experiments for six elderly persons in terms of usability. As a result, the Internet-based cycle ergometer system was effective for continuously supporting the personal fitting procedure.

An Insertion-Deletion system, first introduced in [1], is a theoretical computing model in the DNA computing framework based on insertion and deletion operations. When insertion and deletion operations work together, as expected, they are very powerful. In fact, it has been shown that even the very restricted Insertion-Deletion systems can characterize the class of recursively enumerable languages [1]-[4]. In this paper, we investigate the computational power of Insertion-Deletion systems and show that they preserve the computational universality without using contexts.

Wireless Internet technologies have been developing and users are now able to access more information anywhere through small screen mobile devices. However, due to the limits of cost, bandwidth and screen size in a wireless environment, it is important to minimize interactions between a mobile user and his handheld device, as well as the amount of data transmitted. In this paper we present an interactive evolutionary approach for user-oriented Web search by using mobile devices. To verify this approach, a series of experiments has been conducted. The results show that our approach can allocate the information a user needs within only a few user-system interactions. It substantially reduces the number of retrieved pages a user has to visit. This is especially an important benefit to mobile users.

It is well known that both shape and motion can be factorized directly from the measurement matrix constructed from feature points trajectories under orthographic camera model. In practical applications, the measurement matrix might be contaminated by noises and contains outliers. A direct SVD (Singular Value Decomposition) to the measurement matrix with outliers would yield erroneous result. This paper presents a novel algorithm for computing SVD with outliers. We decompose the SVD computation as a set of alternate linear regression subproblems. The linear regression subproblems are solved robustly by applying the RANSAC strategy. The proposed robust factorization method with outliers can improve the reconstruction result remarkably. Quantitative and qualitative experiments illustrate the good performance of the proposed method.