We present an efficient and fully parallel 2D object recognition method based on the use of a multiscale tree representation of the object boundary and recursive learning of trees. Specifically, the object is represen...
详细信息
We present an efficient and fully parallel 2D object recognition method based on the use of a multiscale tree representation of the object boundary and recursive learning of trees. Specifically, the object is represented by means of a tree where each node, corresponding to a boundary segment at some level of resolution, is characterized by a real vector containing curvature, length, and symmetry of the boundary segment, while the nodes are connected by arcs when segments at successive levels are spatially related. the recognition procedure is formulated as a training procedure made by recursive neural networks followed by a testing procedure over unknown tree structured patterns.
Artificial Neural Networks are applied for solving a wide variety of problems in several areas such as signal processing, robotics, diagnosis, and patternrecognition. these applications demand a high computing power ...
详细信息
Artificial Neural Networks are applied for solving a wide variety of problems in several areas such as signal processing, robotics, diagnosis, and patternrecognition. these applications demand a high computing power and the traditional software implementation are not sufficient. Hardware implementation of neural networks is very interesting due to its high performance and can easily be made parallel. this paper presents a hardware implementation of neural network after training and simulation on the MATLAB software. the excellent hardware performance has been performed through the use of field programmable gate array (FPGA). the diagnosis of the Multi-Purpose Research Reactor of Egypt accidents is used to test the proposed system.
Fractals are a promising framework for several applications other than image coding and transmission, such as database indexing, texture mapping and patternrecognition problems such as writer authentication. However,...
详细信息
Fractals are a promising framework for several applications other than image coding and transmission, such as database indexing, texture mapping and patternrecognition problems such as writer authentication. However, fractal based algorithms are strongly asymmetric because, in spite of the linearity of the decoding phase, the coding process is very time consuming. Many different solutions have been proposed for this problem, but there is not yet a standard for fractal coding. In this paper we analyze the problem of complexity reduction of the image coding phase and providing a new classification technique based on an approximation error measure. We show formally that postponing range/domain comparisons with respect to a preset block, it is possible to reduce the amount of operations needed to encode each range and therefore whole the image. the proposed strategy allows a drastic complexity reduction of the coding phase. the proposed method has been compared with another fractal coding method, showing in which circumstances the proposed algorithm performs better in terms of both bit rate and/or computing time.
Computer Assisted Visual Interactive recognition (CAVIAR) draws on sequential patternrecognition, image database, expert systems, pen computing, and digital camera technology. It is designed to recognize wild flowers...
详细信息
ISBN:
(纸本)076951695X
Computer Assisted Visual Interactive recognition (CAVIAR) draws on sequential patternrecognition, image database, expert systems, pen computing, and digital camera technology. It is designed to recognize wild flowers and other families of similar objects more accurately than machine vision and faster than most laypersons. the novelty of the approach is that human perceptual ability is exploited through interaction withthe image of the unknown object. the computer remembers the characteristics of all previously seen classes, suggests possible operator actions, and displays confidence scores based on already detected features. In one application, consisting of 80 test images of wild flowers, 10 laypersons averaged 80% recognition accuracy, at 12 seconds per flower.
the proceedings contain 27 papers. the special focus in this conference is on Rewriting Techniques and Applications. the topics include: computing and proving;rewriting for deduction and verification;universal interac...
ISBN:
(纸本)3540421173
the proceedings contain 27 papers. the special focus in this conference is on Rewriting Techniques and Applications. the topics include: computing and proving;rewriting for deduction and verification;universal interaction systems with only two agents;general recursion on second order term algebras;beta reduction constraints;from higher-order to first-order rewriting;combining pattern E-unification algorithms;matching power;dependency pairs for equational rewriting;termination proofs by context-dependent interpretations;uniform normalisation beyond orthogonality;verifying orientability of rewrite rules using the knuth-bendix order;relating accumulative and non-accumulative functional programs;context unification and traversal equations;weakly regular relations and applications;on the parallel complexity of tree automata;transfinite rewriting semantics for term rewriting systems;goal-directed e-unification;the unification problem for confluent right-ground term rewriting systems;on termination of higher-order rewriting;matching with free function symbols;deriving focused calculi for transitive relations;a normal form for church-rosser language systems;confluence and termination of simply typed term rewriting systems and parallel evaluation of interaction nets with MPINE.
All the methods for estimating the fundamental matrix do not naturally exploit the rank-2 constraint. For this reason few rank-2 parameterizations of the fundamental matrix have been proposed over the years. In genera...
详细信息
ISBN:
(纸本)0769507506
All the methods for estimating the fundamental matrix do not naturally exploit the rank-2 constraint. For this reason few rank-2 parameterizations of the fundamental matrix have been proposed over the years. In general they can be an over parameterization (12 parameters) being generally valid, or use a minimal set of parameters (eight) but do not cover all the rank-2 matrices. We propose a rank-2 parameterization which uses only 9 parameters, one more of the minimal parameterizations, and covers all the rank-2 matrices.
Due to the increasing use of portable computing and wireless communications systems, energy consumption is of major concern in today's VLSI circuits. Withthat in mind we present an energy conscious weighted rando...
详细信息
ISBN:
(纸本)0769500137
Due to the increasing use of portable computing and wireless communications systems, energy consumption is of major concern in today's VLSI circuits. Withthat in mind we present an energy conscious weighted random pattern testing technique for Built-In-Self-Test (BIST) applications. Energy consumption during BIST operation can be minimized while achieving high fault coverage. Simple measures of observability and controllability of circuit nodes are proposed based on primary input signal probability (probability that a signal is logic ONE). Such measures help determine the testability of a circuit. We developed a tool, POWERTEST, which uses a genetic algorithm based search to determine optimal weight sets (signal probabilities or input signal distribution) at primary inputs to minimize energy dissipations. the inputs conforming to the primary input weight see can be generated using cellular automata or LFSR (Linear Feedback Shift Register). We observed that a single input distribution (or weights) may not be sufficient for some random-pattern resistant circuits, while multiple distributions consume larger area. As a trade-off, two distributions have been used in our analysis. Results on ISCAS benchmark circuits show that energy reduction of up to 97.82% can be achieved (compared to equi-probable random-pattern testing with identical fault coverage) while achieving high fault coverage.
the notion of flexibility (that is, the ability to adapt to changing requirements or execution contexts) is recognized as a key concern in structuring software, and many architectures have been designed to that effect...
详细信息
the notion of flexibility (that is, the ability to adapt to changing requirements or execution contexts) is recognized as a key concern in structuring software, and many architectures have been designed to that effect. However, the corresponding implementations often come with performance and code size overheads. the source of inefficiency can be identified to be in the loose integration of components, because flexibility is often present not only at the design level but also in the implementation. To solve this flexibility vs. efficiency dilemma, we advocate the use of partial evaluation, which is an automated technique to produce efficient, specialized instances of generic programs. As supporting case studies, we consider several flexible mechanisms commonly found in software architectures: selective broadcast, pattern matching, interpreters, software layers, and generic libraries. Using Tempo, our specializer for C, we show how partial evaluation can safely optimize implementations of those mechanisms. Because this optimization is automatic, it preserves the original genericity and extensibility of the implementation.
this paper presents a new checkpointing coordination scheme which utilizes the communication pattern of the cooperating processes. In the proposed scheme, the checkpointing is coordinated for the limited number of pro...
详细信息
ISBN:
(纸本)0818672250
this paper presents a new checkpointing coordination scheme which utilizes the communication pattern of the cooperating processes. In the proposed scheme, the checkpointing is coordinated for the limited number of processes based on the information regarding the communication pattern of the target program. Unlike the previous solutions which do not utilize the communication pattern, it is possible to reduce the coordination effort as well as the checkpointing frequency. Extensive simulation has been performed to evaluate the performance of the proposed scheme and we concluded that the proposed scheme significantly reduces the checkpointing overhead compared withthe loose coordination schemes.
there have been many adaptive routing algorithms proposed in the literature for wormhole-routed networks. this paper compares the performance of deterministic routing to two adaptive routing algorithms in the cube net...
详细信息
there have been many adaptive routing algorithms proposed in the literature for wormhole-routed networks. this paper compares the performance of deterministic routing to two adaptive routing algorithms in the cube network. the comparison takes into account router delays introduced by adaptivity. the results show that in certain circumstances, deterministic routing can outperform adaptive routing.
暂无评论