Cascaded linear shift-invariant processors in optical pattern recognition

We study a cascade of linear shift-invariant processing modules (correlators), each augmented with a nonlinear threshold as a means to increase the performance of high-speed optical pattern recognition. This configuration is a special class of multilayer, feed-forward neural networks and has been proposed in the literature as a relatively fast best-guess classifier. However, it seems that, although cascaded correlation has been proposed in a number of specific pattern recognition problems, the importance of the configuration has been largely overlooked. We prove that the cascaded architecture is the exact structure that must be adopted if a multilayer feed-forward neural network is trained to produce a shift-invariant output. In contrast with more generalized multilayer networks, the approach is easily implemented in practice with optical techniques and is therefore ideally suited to the high-speed analysis of large images. We have trained a digital model of the system using a modified backpropagation algorithm with optimization using simulated annealing techniques. The resulting cascade has been applied to a defect recognition problem in the canning industry as a benchmark for comparison against a standard linear correlation filter, the minimum average correlation energy (MACE) filter. We show that the nonlinear performance of the cascade is a significant improvement over that of the linear MACE filter in this case.     

Developing linear error models for analog devices

Techniques are presented for developing linear error models for analog and mixed-signal devices. A simulation program developed to understand the modeling process is described, and results of simulations are presented. Methods for optimizing the size of empirical error models based on simulated error analyses are included. Once established, the models can be used in a comprehensive approach for optimizing the testing of the subject devices. Models are developed using data from a group of 13-bit A/D converters and compared with the simulation results     

Projection-slice synthetic discriminant functions for optical pattern recognition

The projection-slice synthetic discriminant function (PSDF) filter is introduced and proposed for distortion-invariant pattern-recognition applications. The projection-slice theorem, often used in tomographic applications for medical imaging, is utilized to implement a distortion-invariant filter. Taking M projections from one training image and combining them with (N - 1)M projections taken from another N - 1 training image accomplishes this. With the projection-slice theorem, each set of these M projections can be represented as M one-dimensional slices of the two-dimensional Fourier transform of the particular training image. Therefore, the PSDF filter has the advantage of matching each of the training images with at least M slices of their respective Fourier transforms. This filter is theoretically analyzed, numerically simulated, and experimentally implemented and tested to verify the simulation results. These tests show that the PSDF filter significantly outperforms the matched-filter and the basic synthetic discriminant function technique for the particular images used.     

Convolution-kernel-based optimal trade-off filters for optical pattern recognition

An architecture for the implementation of optical pattern recognition is proposed that makes use of convolution-kernel-based optimal trade-off filters to allow for an increased speed of operation and filter storage capability. The derivation of these new convolution-kernel-based optimal trade-off filters is presented, and their noise robustness and discrimination capabilities are discussed.     

Color encoding for polychromatic single-channel optical pattern recognition

The common multichannel system for recognizing colored images is replaced by a color-encoded single-channel system. Amethod inspired by the Munsell color system is used for encoding the different colors as phase and amplitude functions. It is shown that for many practical cases the phase information part of the color code is sufficient for obtaining good results. An implementation based on a liquid-crystal television panel that works in a phase-modulation mode is suggested. Computer simulations that demonstrate the capabilities of the suggested method are given as well as a comparison with previously published multichannel performance.     

U-tests for variance components in linear mixed models

We propose a U-statistics-based test for null variance components in linear mixed models and obtain its asymptotic distribution (for increasing number of units) under mild regularity conditions that include only the existence of the second moment for the random effects and of the fourth moment for the conditional errors. We employ contiguity arguments to derive the distribution of the test under local alternatives assuming additionally the existence of the fourth moment of the random effects. Our proposal is easy to implement and may be applied to a wide class of linear mixed models. We also consider a simulation study to evaluate the behaviour of the U-test in small and moderate samples and compare its performance with that of exact F-tests and of generalized likelihood ratio tests obtained under the assumption of normality. A practical example in which the normality assumption is not reasonable is included as illustration.     

General linear optical coordinate tranformations

New optical configurations for performing general coordinate transformation operations of shear, rotation, and their combination are presented. These configurations consist of refractive spherical and cylindrical lenses that are readily available. Typically, high-resolution imagery can be obtained, depending on the size of the input object, the illumination wavelength, and the f-number of the lenses. Basic and more general configurations are presented, along with experimental results clearly showing image shearing, rotation, and a combination of these with high-quality output imagery.     

用于Android手机活动识别的深度重构模型

基于数据的流形假设,进行了Android手机的活动识别研究,提出了一种深度重构模型(DRMs),该模型无需基础几何的先验假设就能自动学习到当前类样本的复杂非线性曲面结构和几何特点。首先定义了一个深度重构模型(DRM)模板,通过高斯受限玻尔兹曼机(GRBMs)逐层贪婪训练以初始化DRM模板的权重。在训练阶段,根据每类样本分别微调初始化后的DRM模板便可得到特定类的DRM。在测试阶段,基于测试样本与特定类DRM的最小重构误差决策活动类别。实验证明,该方法对Android手机数据集的活动识别正确率高达99%。     

Confidence and prediction intervals for generalised linear accident models

Generalised linear models, with "log" link and either Poisson or negative binomial errors, are commonly used for relating accident rates to explanatory variables. This paper adds to the toolkit for such models. It describes how confidence intervals (for example, for the true accident rate at given flows) and prediction intervals (for example, for the number of accidents at a new site with given flows) can be produced using spreadsheet technology.     

Rotation-invariant optical recognition of three-dimensional objects

An automatic method for rotation-invariant three-dimensional (3-D) object recognition is proposed. The method is based on the use of 3-D information contained in the deformed fringe pattern obtained when a grating is projected onto an object's surface. The proposed method was optically implemented by means of a two-cycle joint transform correlator. The rotation invariance is achieved by means of encoding with the fringe pattern a single component of the circular-harmonic expansion derived from the target. Thus the method is invariant for rotations around the line of sight. The whole experimental setup can be constructed with simple equipment. Experimental results show the utility of the proposed method.     

Object recognition using three-dimensional optical quasi-correlation

A novel method of three-dimensional (3-D) object recognition is proposed. Several projections of a 3-D target are recorded under white-light illumination and fused into a single complex two-dimensional function. After proper filtering, the resulting function is coded into a computer-generated hologram. When this hologram is coherently illuminated, a correlation space is reconstructed such that light peaks indicate the existence and locations of true targets in the observed 3-D scene. Experimental results and comparisons with results of another 3-D object recognition technique are presented.     

Hybrid incoherent optical pattern recognition system

A pattern recognition system that uses incoherent spatial filtering to recognize images directly from a narrowband phosphor television monitor is described. Images of real objects are captured with a television camera. These images are then edge-enhanced electronically and displayed on the TV monitor. The monitor output is used directly as the input to a holographic correlator. An optical multichannel analyzer at the correlation plane is used to analyze the shape of the correlation function and to determine the position of its peak. Experimental results agree well with theory. Concepts for handling rotation, aspect angle, and scale variations of the input are discussed.     

Hierarchical modeling using generalized linear models

In a complex manufacturing environment, there are hundreds of interrelated processes that form a complex hierarchy. This is especially true of semiconductor manufacturing. In such an environment, modeling and understanding the impact of critical process parameters on final performance measures such as defectivity is a challenging task. In addition, a number of modeling issues such as a small number of observations compared to process variables, difficulty in formulating a high‐dimensional design matrix, and missing data due to failures pose challenges in using empirical modeling techniques such as classical linear modeling as well as generalized linear modeling (GLM) approaches. Our approach is to utilize GLM in a hierarchical structure to understand the impact of key process and subprocess variables on the system output. A two‐level approach, comprising subprocess modeling and meta‐modeling, is presented and modeling related issues such as bias and variance estimation are considered. The hierarchical GLM approach helps not only in improving output measures, but also in identifying and improving subprocess variables attributed to poor output quality. Copyright © 2011 John Wiley & Sons, Ltd.     

Coupling recognition of the structure and parameters of non‐linear constitutive material models using hybrid evolutionary algorithms

The structure of the non‐linear constitutive models is a key to control non‐linear behaviours of materials. Because the non‐linear mechanical mechanism is not clearly understood in most cases, it is very difficult to assume the structure of the model in advance. The recognition of the structure of the model from experimental results can help understanding of the mechanism. This recognition is a dynamic search problem being highly multimodal, multi‐variable with high order, and needing a large parameter space. How to obtain a global optimum solution is a key to this problem. In this paper, a hybrid evolutionary algorithm is proposed for coupling recognition of the structure of the non‐linear constitutive material model and its coefficients in global space using global response information, e.g. load vs deflection data, obtained from the structural test. Genetic programming is used to recognize the structure of the non‐linear stress–strain relationship without any assumption in advance and the genetic algorithm is then used to recognize its coefficients. The non‐linear stress–strain relationship thus found can not only satisfy the dynamic change in its structure but also its variables and coefficients. Non‐linear finite element analysis is used to transfer the load–deflection information to the stress–strain data. The potential of the proposed method is demonstrated by applying it to the macro‐mechanical modelling of the non‐linear behaviour of composite materials. A non‐linear material model for the unidirectional ply is recognized by using experimental data of a lamina plate [(±45)₆]_s. The obtained non‐linear constitutive model gave good predictions in coincidence with the non‐linear behaviours of the [(±30)₆]_s, [(0/±45)₃]_s and [(0/±45)₄]_s plates. The results indicate that the coupling non‐linear constitutive model of the structure and its coefficients can identify the model which the traditional constitutive model theory is unable to recognize. Copyright © 2004 John Wiley & Sons, Ltd.     

Characterization of a trajectory recognition optical sensor for anautomated guided vehicle

Characterization of a relatively simple optical sensor used for recognition of the desired fixed trajectory for an automated guided vehicle, painted on an industrial shop floor, is described. The optical sensor consists of 14 infrared emitter-detector pairs arranged in two columns and is fixed underneath the vehicle chassis. A microcomputer-based test platform for evaluation of the proposed sensor is also described. The sensor performance is evaluated using two geometrical algorithms and one based on neural networks, with the latter giving better results     

Measurement of linear accelerations using optical radiation

An expression for the relativistic frequency shift in a two-channel optical accelerometer is obtained and it is shown that, from the standpoint of applications, it is functionally analogous to a mechanical accelerometer, i.e., it is a gauge of the apparent acceleration.Translated from Izmeritelnaya Tekhnika, No. 10, pp. 31–32, October, 2004.