Regression classifier in adaptive technical vision system

The authors examined vector quantizer performance as a function of training sequence size for tree-structured and full-search vector quantizers. The performance was measured by the mean-squared error between the input image and the quantizer output at a given bit rate. The training sequence size was measured either by the number of training images, or by the number of training vectors. When the training vectors were counted, they were selected randomly from among the training images. For every training sequence size, vector quantizers were developed from several different training sequences, and the distortion was calculated for different test sequences in a cross validation procedure. Preliminary results suggest that plots of distortion vs. number of training images follow an algebraic decay, as expected from analogous results of learning theory. >

Network anomaly detection is a critical task to ensure network security. With increasing network traffic, detecting network anomaly would require solving a large-scale pattern classification problem that often contains millions of training vectors. Each training vector may represent a particular signature of network traffic pattern and some of them may be linked to security breaching activities that need to be detected and eradicated. In this paper, a popular statistical learning algorithm known as the support vector machine (SVM) was consider to solve the network anomaly detection problem. However, it is well known that SVM would require excessively long computing time and exceedingly large amount of memory when number of training vectors becomes huge. Hence, direct application of the standard SVM algorithm to solve large-scale network anomaly detection problems is impractical. In this paper, based on computational geometry theory, a new algorithm called convex-hull SVM (CH-SVM) was proposed, which can yield the same solution as original SVM while using significantly less training data, and hence less computing time. Then experiments were done on KDD'99 intrusion detection dataset to compare the performance of the proposed algorithm to a standard SVM and observed reduced training time and improved classification accuracy.

In this chapter, we continue our study of Banach and Hilbert spaces. Here, we mainly consider linear functionals, i.e., additive, homogeneous, and continuous number functions given on such spaces. The problems under consideration are mostly grouped around two fundamental facts, namely, the Hahn-Banach theorem on extensions of linear functionals and the Banach-Steinhaus theorem (the principle of uniform boundedness). The general form of linear continuous functionals in many important spaces and some geometric problems in the theory of Hilbert spaces are also investigated.

Context. The SLAM problem solving for an autonomous mobile robot requires efficient technical means for surrounding terrain scanning with the purpose of its mapping and obstacles detecting. As such means, laser scanning systems are widely used both independently and in combination with other tools as a part of a uniform technical vision system of a mobile robot. One of the problems with a technical vision systems operation is the ability to detect relatively small obstacles, which requires scanning of a limited sector within the field of view or even focusing on a specific point of space. This study is devoted to the issue of improving the reliability of obstacles detecting within the robot field of view by improving the laser actuator of the technical vision system. Objective. The objective of the work is to the reliability increasing of obstacles detection within the robot technical vision system field of view due to the robust control of the actuators of the positioning system of the laser. Method. The classical PD-controller for the laser positioning actuator, which meets the requirements for the quality of the transient process, has been synthesized. The evaluation of robust properties of the obtained control system showed both a significant dependence of the actuator dynamic properties on the variation of the values of the actuator model parameters and the potential possibility of its time response increasing. With the help of the MATLAB Robust Control Toolbox, the controller gains have been redefined to ensure the robust properties of the control system. The analysis of the influence of parametric uncertainties of the actuator model on the system dynamic properties is conducted. Results. A robust PD-controller for the laser beam positioning system actuator for the technical vision system has been synthesized. It combines the simplicity of the implementation of a classic controller with a weak sensitivity to the uncertainties presence. Conclusions. The using of the controller at the mobile robot laser technical vision system will increase the reliability of obstacle detection and, as a result, the accuracy of mapping of a limited sector within the robot field of view under the conditions of the parametric uncertainty of the actuator model.

Valued constraint satisfaction problems (VCSPs) are a large class of combinatorial optimisation problems. The computational complexity of VCSPs depends on the set of allowed cost functions in the input. Recently, the computational complexity of all VCSPs for finite sets of cost functions over finite domains has been classified. Many natural optimisation problems, however, cannot be formulated as VCSPs over a finite domain. We initiate the systematic investigation of the complexity of infinite-domain VCSPs with piecewise linear homogeneous cost functions. Such VCSPs can be solved in polynomial time if the cost functions are improved by fully symmetric fractional operations of all arities. We show this by reducing the problem to a finite-domain VCSP which can be solved using the basic linear program relaxation. It follows that VCSPs for submodular PLH cost functions can be solved in polynomial time; in fact, we show that submodular PLH functions form a maximally tractable class of PLH cost functions.

We generalize our earlier results from [9] on the Bessmertnyĭ class of operator-valued functions holomorphic in the open right poly-halfplane which admit representation as a Schur complement of a block of a linear homogeneous operator-valued function with positive semidefinite operator coefficients, to the case of a product of open right matrix halfplanes. Several equivalent characterizations of this generalized Bessmertnyĭ class are presented. In particular, its intimate connection with the Agler-Schur class of holomorphic contractive operator-valued functions on the product of matrix unit disks is established.KeywordsSeveral complex variableshomogeneouspositiveholomorphicoperator-valued functionsproduct of matrix halfplaneslong resolvent representationsAgler-Schur class

The article presents a methodology for substantiation of requirements for the technical vision system of a robotic complex. A technical vision system of the robotic complex is viewed as a combination of two subsystems: measurement and recognition. To implement the methodology we developed methods for calculating partial optimality criteria for substantiation of the technical requirements and evaluation of search area of the optimal values of measuring instruments characteristics of the technical vision system of a robotic complex; a recursive procedure for choosing the optimal values of measuring instruments characteristics of the technical vision system; a scheme of trade-off for evaluating the optimal technical requirements for advanced measurement instruments of the technical vision system in different technical and economical conceptions. The search for optimal solution is done according to partial optimality criteria: recognition efficiency, the cost and risks of creating measuring instruments. For creating the recursive procedure based on formulated assumptions and assertions, a criterion, which provides the search of Pareto-optimal solutions, was synthesized. The developed methodology takes into account the existing (more suitable) technical and economical conceptions of creating a robotic complex while choosing trade-offs.

Along with the rapid development of computer and image processing technology, it is definitely convenient to obtain various images for subjects, which can be more robust to classification as more feature information is contained. However, how to effectively exploit the rich discriminative information within image sets is the key problem. In this paper, based on the concept of dual linear regression classification method for image set classification, we propose a novel discriminative framework to exploit the superiority of discriminant regression mechanism. We aim to learn a projection matrix to force the represented image points from the same class to be close and those from different class are better separated. The feature extraction strategy in our discriminative framework can appropriately work with the corresponding classification strategy, thus, better classification performance can be achieved. Moreover, we propose a kernel discriminative extension method to address the non-linearity problem by adopting the kernel trick. From the experimental results, our proposed method can obtain competitive recognition rates on face recognition tasks via mapping the original image sets into a more discriminative feature space. Besides, it also shows the effectiveness for object classification task with small image sizes and different number of frames.

Glass artifacts are easily weathered by environmental influences during burial, and the internal chemical composition is exchanged with the external environment, resulting in changes in its composition ratio. For archaeological interrogation, it is of great significance to study the chemical composition of glass before and after weathering and related issues. In this paper, a support vector machine model is used to reasonably separate the data points of high potassium glass and lead-barium glass, and a linear classification function is derived, i.e., the classification law of the two types of glass is obtained. Then, this paper performs R-type cluster analysis on the chemical composition indexes first, and reduces the dimensionality of several indexes; then performs Q-type cluster analysis on the sample detection points, and performs a one-way ANOVA test on the classification scheme of different numbers of subclasses obtained, and finally divides them into four subclasses. On this basis, the data of the unknown class of glass artifacts are substituted into the trained support vector machine model, and the type to which they belong can be determined by calculating the value of the judgment linear classification function.

This paper proposes an advancement in the application of a Technical Vision System (TVS), which integrates a laser scanning mechanism with a single light sensor to measure 3D spatial coordinates. In this application, the system is used to scan and digitalize objects using a rotating table to explore the potential of the system for 3D scanning at reduced resolutions. The experiments undertaken searched for optimal scanning windows and used statistical data filtering techniques and regression models to find a method to generate a 3D scan that was still recognizable with the least amount of 3D points, balancing the number of points scanned and time, while at the same time reducing effects caused by the particularities of the TVS, such as noise and entropy in the form of natural distortion in the resulting scans. The evaluation of the experimentation results uses 3D point registration methods, joining multiple faces from the original volume scanned by the TVS and aligning it to the ground truth model point clouds, which are based on a commercial 3D camera to verify that the reconstructed 3D model retains substantial detail from the original object. This research finds it is possible to reconstruct sufficiently detailed 3D models obtained from the TVS, which contain coarsely scanned data or scans that initially lack high definition or are too noisy.

The work reports development of the technical vision system (TVS), included into the metal structure arc welding process automatic control system in shipbuilding. Version of construction and optimization of the sensor system (SS) of TVS and its main componenets - irradiation and television unit (ITU) and program and computer system are considered. TVS allows to control geometrical parameters of the butt of joined parts of various configurations and welded seam and also develops signals on control of matched movement of a torch with real line of a welded joint, adjustment of feed of welding components (wire, fluxes, gases) and arc welding parameters. The non-contact method of triangulation measurement, used in TVS, provides resolution of geometrical sizes in real time scale not lower than 50 μm.

This paper presents a novel marginal Fisher regression classification (MFRC) method by incorporating the ideas of marginal Fisher analysis (MFA) and linear regression classification (LRC). The MFRC aims at minimizing the within-class compactness over the between-class separability to find an optimal embedding matrix for the LRC so that the LRC on that subspace achieves a high discrimination for classification. Specifically, the within-class compactness is measured with the sum of distances between each sample and its neighbors within the same class with the LRC, and the between-class separability is characterized as the sum of distances between margin points and their neighboring points from different classes with the LRC. Therefore, the MFRC embodies the ideas of the LRC, Fisher analysis and manifold learning. Experiments on the FERET, PIE and AR datasets demonstrate the effectiveness of the MFRC.

One of the most important problems in pattern recognition is texture-based image classification. In this paper, the combination of Discrete Cosine Transform (DCT) and Gray Level Co-Occurrence Matrix (GLCM) methods for feature extraction was proposed. The attributes extracted from DCT method were mean and variance, while the attributes extracted from GLCM method were energy and entropy. Adaptive Neuro-Fuzzy Inference System (ANFIS) was used as a classifier. The classifier model was trained using 50% of the texture images and remaining images were used for testing. Four classes of texture images were downloaded from KTH-TIPS (Textures under varying Illumination, Pose and Scale) image database, three of which were used in each experiments thus there were four data combination. The best data testing accuracy result towards textures of crumpled aluminium foil, corduroy, and orange peel is 98.3%, which is 1.6% better than one hidden-layer feed forward neural network classifier. In average, testing accuracy result of ANFIS excelled one hidden-layer feed forward neural network with 93.7% over 90.4%.

The creation of new generations of autonomous robotic complexes, recognition systems and vision systems in general is impossible without the use of modern computer technology. This article contains models of technical vision system of robots based on Elbrus microprocessors. Models of detection, classification and segmentation tasks were developed. Theoretical and experimental results were obtained on actual and perspective Elbrus microprocessors. It is shown that Elbrus microprocessors can be the base for onboard technical vision system. The results obtained by the authors indicate the prospects of import substitution in the field of robotics.

A two-phase procedure for calculation of multiple linear classification functions has been developed. Phase I approximates the distribution of samples in the measurement space by a series of linear functions and preselects only those samples lying in the critical region. Phase II utilizes the reduced number of samples for calculation by a linear programming algorithm, the multiple linear classification functions that can separate given samples strictly. The procedure was applied to the problem of spoken-word recognition. About 3300 samples of Japanese spoken digits, uttered by 55 male speakers and represented as 56-dimensional measurement vectors by a vocoder-type frequency analyzer are collected. During Phase I, the number was reduced to 16 linear functions on the average. Precise classification functions were then calculated for each digit in Phase II. Most of the digits were separated by a single linear function while others were separated by two functions. An error rate of less than 0.2% was achieved for 550 samples newly uttered by the same 55 speakers.