A sequential dynamic heteroassociative memory for multistep pattern recognition and one-to-many association

Bidirectional associative memories (BAMs) have been widely used for auto and heteroassociative learning. However, few research efforts have addressed the issue of multistep vector pattern recognition. We propose a model that can perform multi step pattern recognition without the need for a special learning algorithm, and with the capacity to learn more than two pattern series in the training set. The model can also learn pattern series of different lengths and, contrarily to previous models, the stimuli can be composed of gray-level images. The paper also shows that by adding an extra autoassociative layer, the model can accomplish one-to-many association, a task that was exclusive to feedforward networks with context units and error backpropagation learning.     

A feedforward bidirectional associative memory

In contrast to conventional feedback bidirectional associative memory (BAM) network models, a feedforward BAM network is developed based on a one-shot design algorithm of O(p(2)(n+m)) computational complexity, where p is the number of prototype pairs and n, m are the dimensions of the input/output bipolar vectors. The feedforward BAM is an n-p-m three-layer network of McCulloch-Pitts neurons with storage capacity 2(min{m,n}) and guaranteed perfect bidirectional recall. The overall network design procedure is fully scalable in the sense that any number p=/<2(min{m,n}) of bidirectional associations can be implemented. The prototype patterns may be arbitrarily correlated. With respect to inference performance, it is shown that the Hamming attractive radius of each prototype reaches the maximum possible value. Simulation studies and comparisons illustrate and support these theoretical developments.     

On multiple training for bidirectional associative memory

The minimal number of times for using a pair for training to guarantee recall of that pair among a set of training pairs is derived for a bidirectional associative memory.     

Two coding strategies for bidirectional associative memory

Enhancements of the encoding strategy of a discrete bidirectional associative memory (BAM) reported by B. Kosko (1987) are presented. There are two major concepts in this work: multiple training, which can be guaranteed to achieve recall of a single trained pair under suitable initial conditions of data, and dummy augmentation, which can be guaranteed to achieve recall of all trained pairs if attaching dummy data to the training pairs is allowable. In representative computer simulations, multiple training has been shown to lead to an improvement over the original Kosko strategy for recall of multiple pairs as well. A sufficient condition for a correlation matrix to make the energies of the training pairs be local minima is discussed. The use of multiple training and dummy augmentation concepts are illustrated, and theorems underlying the results are presented.     

A Boolean Hebb rule for binary associative memory design

A binary associative memory design procedure that gives a Hopfield network with a symmetric binary weight matrix is introduced in this paper. The proposed method is based on introducing the memory vectors as maximal independent sets to an undirected graph, which is constructed by Boolean operations analogous to the conventional Hebb rule. The parameters of the resulting network is then determined via the adjacency matrix of this graph in order to rind a maximal independent set whose characteristic vector is close to the given distorted vector. We show that the method provides attractiveness for each memory vector and avoids spurious memories whenever the set of given memory vectors satisfy certain compatibility conditions, which implicitly imply sparsity. The applicability of the design method is finally investigated by a quantitative analysis of the compatibility conditions.     

A simple method for improving local binary patterns by considering non-uniform patterns

The basic idea behind LBP is that an image is composed of micropatterns. A histogram of these micropatterns contains information about the local features in an image. These micropatterns can be divided into two types: uniform and non-uniform. In standard applications using LBP, only the uniform patterns are used. The non-uniform patterns are considered in only a single bin of the histogram that is used to extract features in the classification stage. Non-uniform patterns have undesirable characteristics: they are of a high dimension, partially correlated, and introduce unwanted noise. To offset these disadvantages, we explore using random subspace, well-known to work well with noise and correlated features, to train features based also on non-uniform patterns. We find that a stand-alone support vector machine performs best with the uniform patterns and random subspace with histograms of 50 bins performs best with the non-uniform patterns. Superior results are obtained when the two are combined. Based on extensive experiments conducted in several domains using several benchmark databases, it is our conclusion that non-uniform patterns improve classifier performance.     

A feasible computer system for grey-level,pictorial pattern recognition

A general-purpose interactive hardware-software system is described which allows the analysis, representation and enhancement of poor quality, multiple-frame, grey-level pictures. A precise, computer-controlled, high-speed, random-access flying-spot scanner is used. Contour-finding, piece-wise linear fitting and global region-extraction algorithms with an interactive executive program are described. The results obtained when the system was applied to straight line drawings and cine-angiograms are given.     

Encoding strategy for maximum noise tolerance bidirectional associative memory

In this paper, the basic bidirectional associative memory (BAM) is extended by choosing weights in the correlation matrix, for a given set of training pairs, which result in a maximum noise tolerance set for BAM. We prove that for a given set of training pairs, the maximum noise tolerance set is the largest, in the sense that this optimized BAM will recall the correct training pair if any input pattern is within the maximum noise tolerance set and at least one pattern outside the maximum noise tolerance set by one Hamming distance will not converge to the correct training pair. This maximum tolerance set is the union of the maximum basins of attraction. A standard genetic algorithm (GA) is used to calculate the weights to maximize the objective function which generates a maximum tolerance set for BAM. Computer simulations are presented to illustrate the error correction and fault tolerance properties of the optimized BAM.     

Diurnal patterns of bidirectional vegetation indices for wheat canopies

The perpendicular vegetation index (PVI) and normalized difference vegetation index (NDVI) were calculated from Mark II radiometer RED (0.63-0.69 μm) and NIR (0.76–0.90 μ) bidirectional radiance observations for wheat canopies. Measurements were taken over the plant development interval flag leaf expansion to watery ripeness of the kernels during which the leaf area index (LAI) decreased from 40 to 2-5. Spectral data were taken on four cloudless days five times (09.30, 11.00, 12.30, 14.00 and 15.30 hours (central standard time, C.S.T.) at five view zenith, Zv (0, 15, 30,45 and 60°) and eight view azimuth angles relative to the Sun, A_v (0, 45, 90, 135, 180, 225, 270 and 315°). The PVI was corrected to a common solar irradiance (PVIC) based on simultaneously observed insolation readings.

The PVIC at nadir view (?=0°) increased as (l/cosZ_s) increased on all the measurement days whereas the NDVI changed little as solar zenith angle (Z_s) changed. Thus, the PVIC responded to increasing path length through the canopy, or the number of leaves encountered, as solar zenith angle changed whereas the NDVI, which has saturated by the time an LAI of 2 was achieved, was nonresponsive.

Off-nadir PVIC ratioed to nadir PVIC increased as the view zenith and solar zenith angles increased (reciprocity in Sun and view angles), and as the view azimuth, A angle approached the Sun position (back scattering stronger that forwardscattering). In contrast, the DNVI was very stable for all view and solar angles consistent with saturation in its response. Even though the PVI is subject to bidirectional effects, it contains more useful information about wheat canopies at LAI > 2 than does the NDVI. The NDVI of the plant canopies changed rapidly at low vegetative cover but its bidirectional sensitivity at low LAI was not investigated.     

Encoding method for bidirectional associative memory usingprojection on convex sets

The traditional encoding method of bidirectional associative memory (BAM) suggested by Kosko (1988) is based on the correlation method with which the capacity is very small. The enhanced Householder encoding algorithm (EHCA) presented here is developed on the basis of the Householder encoding algorithm (HCA) and projection on convex sets (POCS). The capacity of BAM with HCA tends to the dimension of the pattern pairs. Unfortunately, in BAM with HCA there are two different interconnection matrices and hence BAM with HCA may not converge when the initial stimulus is not one of the library patterns. In EHCA the two matrices found by HCA are reduced into one matrix by POCS. Hence, the convergent property of BAM can be maintained. Simulation results show that the capacity of BAM with EHCA is greatly improved.     

Dynamic bidirectional associative memory using chaotic neurons

A dynamic bidirectional associative memory (DBAM) with chaotic neurons as nodes is proposed. A learning algorithm based on Pontryagin’s minimum principle makes the DBAM equivalent to any other BAM so far reported. The input selection mechanism gives the DBAM the additional ability of multiple memory access, which is based on the dynamics of the chaotic neuron. This work was presented, in part, at the Fourth International Symposium on Artificial Life and Robotics, Oita, Japan, January 19–22, 1999     

Multi-structure local binary patterns for texture classification

Recently, the local binary patterns (LBP) have been widely used in the texture classification. The LBP methods obtain the binary pattern by comparing the gray scales of pixels on a small circular region with the gray scale of their central pixel. The conventional LBP methods only describe microstructures of texture images, such as edges, corners, spots and so on, although many of them show good performances on the texture classification. This situation still could not be changed, even though the multi-resolution analysis technique is adopted by LBP methods. Moreover, the circular sampling region limits the ability of the conventional LBP methods in describing anisotropic features. In this paper, we change the shape of sampling region and get an extended LBP operator. And a multi-structure local binary pattern (Ms-LBP) operator is achieved by executing the extended LBP operator on different layers of an image pyramid. Thus, the proposed method is simple yet efficient to describe four types of structures: isotropic microstructure, isotropic macrostructure, anisotropic microstructure and anisotropic macrostructure. We demonstrate the performance of our method on two public texture databases: the Outex and the CUReT. The experimental results show the advantages of the proposed method.     

将局部二进制模式应用于动态纹理识别的新方法

动态纹理的处理、描述与识别是纹理分析的热门领域。动态纹理是对普通纹理在时间域方面的扩展,包括动态特征和静态特征。基于LBP算法的扩展提出的VLBP算法较好的描述了动态纹理特征,但是计算量过大,模板过多。本文提出了一种由VLBP算法改进的基于局部二进制运动模式的特征提取方法用以动态纹理的描述和识别,它包括提取动态特征和提取静态特征两部分。将LBP算子做为块匹配准则提取局部二进制运动模式柱状图做为动态特征的描述,提取LBP柱状图做为静态特征的描述,并将二者连接得出描述动态纹理特征的联合的局部二进制运动模式柱状图。通过对DynTex集实验的结果表明,本文提出的方法在性能和识别率方面均要优于VLBP。     

Local binary patterns for a hybrid fingerprint matcher

In this work, we present a novel hybrid fingerprint matcher system based on local binary patterns. The two fingerprints to be matched are first aligned using their minutiae, then the images are decomposed in several overlapping sub-windows, each sub-window is convolved with a bank of Gabor filters and, finally, the invariant local binary patterns histograms are extracted from the convolved images.Extensive experiments conducted over the four FVC2002 fingerprint databases show the effectiveness of the proposed hybrid approach with respect to the well-known Tico's minutiae matcher and other image-based approaches. Moreover, a BioHashing approach have been designed using the proposed fixed-length feature vector and very interesting performance has been obtained by combining it with the Tico's minutiae matcher.     

Periodic oscillation of discrete-time bidirectional associative memory neural networks

In this paper, a discrete-time bidirectional associative memory neural networks model is considered. By employing the theory of coincidence degree and using Halanay-type inequality technique we give some sufficient conditions ensuring the existence and globally exponential stability of periodic solutions for the discrete-time bidirectional neural networks. An example with the numerical simulations is provided to show the correctness of our analysis.