Open Access Open Access  Restricted Access Access granted  Restricted Access Subscription Access

Vol 28, No 4 (2018)

Proceedings of the 6th International Workshop

An Enhanced Histogram of Oriented Gradient Descriptor for Numismatic Applications

Hmood A.K., Suen C.Y., Lam L.

Abstract

The Histogram of Oriented Gradients (HOG) is one of the most widely used methods to extract the gradient features for object recognition and consistently shows high accuracy rates when compared to other descriptors. The major drawbacks of using the HOG method are the necessity of finding an optimal window size to fit the whole object; and the exhaustive search mechanism represented by a fixed window size sliding through the whole image to locate and recognize objects. This research proposes an efficient and robust Dynamic-HOG as an improvement to the traditional HOG method to locate and recognize structured objects in images. The proposed method works by locating and analyzing the structured objects in images in order to define a dynamic window size w.r.t. each object size. Moreover, the Dynamic-HOG method requires much less processing time by eliminating the exhaustive search mechanism. The method defines the height and width thresholds of objects and bounds each object with a window w.r.t. its size while ignoring non–object edges. It fits structured objects of a close range of heights and widths. This paper considers the characters that are minted on coins of different languages and sizes as the objects to recognize. There are several papers in the literature discussing coin recognition problem and proposing solutions based on various sets of features extracted from the entire coin image. This research also proposes a new method for coin recognition by focusing on recognize coins based on smaller part of the coin image which are the characters. Our method is evaluated on coins from diverse countries with different background complexity. The proposed method achieved precision and recall rates as high as 98.08 and 98.23%, respectively; which demonstrate the effectiveness and robustness of the proposed method.

Pattern Recognition and Image Analysis. 2018;28(4):569-587
pages 569-587 views

The Grid Methods of the Recognition of the Region of Efficiency of Microwave Devices

Antonova G.M.

Abstract

Some results for design and optimization of complex microwave devices are considered in this article. The problems are investigated from the standpoint of recognition of region of efficiency in which necessary values of given output characteristics are appeared. The application for optimization of meshes that are uniform in the multidimensional space of parameters is discussed. The solution of the approximate optimization problem using a specially created mathematical model of the device and software packages that implement time-consuming computational procedures is debated.

Pattern Recognition and Image Analysis. 2018;28(4):588-594
pages 588-594 views

On Metric Correction and Conditionality of Raw Featureless Data in Machine Learning

Dvoenko S.D., Pshenichny D.O.

Abstract

Recently, raw experimental data in machine learning often appear as direct comparisons between objects (featureless data). Different ways to evaluate difference or similarity of a pair of objects in image and data mining, image analysis, bioinformatics, etc., are usually used in practice. Nevertheless, such comparisons often are not distances or correlations (scalar products) like a correct function defined on a limited set of elements in machine learning. This problem is denoted as metric violations in ill-posed matrices. Therefore, it needs to recover violated metrics and provide optimal conditionality of corresponding matrices of pairwise comparisons for distances and similarities. This is the correct basis for using of modern machine learning algorithms.

Pattern Recognition and Image Analysis. 2018;28(4):595-604
pages 595-604 views

Detecting Animals in Infrared Images from Camera-Traps

Follmann P., Radig B.

Abstract

Camera traps mounted on highway bridges capture millions of images that allow investigating animal populations and their behavior. As the manual analysis of such an amount of data is not feasible, automatic systems are of high interest. We present two different of such approaches, one for automatic outlier classification, and another for the automatic detection of different objects and species within these images. Utilizing modern deep learning algorithms, we can dramatically reduce the engineering effort compared to a classical hand-crafted approach. The results achieved within one day of work are very promising and are easily reproducible, even without specific computer vision knowledge.

Pattern Recognition and Image Analysis. 2018;28(4):605-611
pages 605-611 views

Development and Experimental Investigation of Mathematical Methods for Automating the Diagnostics and Analysis of Ophthalmological Images

Gurevich I.B., Yashina V.V., Ablameyko S.V., Nedzved A.M., Ospanov A.M., Tleubaev A.T., Fedorov A.A., Fedoruk N.A.

Abstract

The paper summarizes the joint work of specialists in the fields of image analysis and ophthalmology over the last few years. As a result of this work, new mathematical methods for automating image analysis that have important diagnostic value for ophthalmology have been developed: (1) identification of the lipid layer state in the intermarginal space of human eyelids; (2) analysis of the degree of cellular structure density (cellularity) in the corneal tissue of human eyes; (3) identification of the state of the retinal blood flow when analyzing fluorescent angiograms of the human fundus; and (4) morphometric analysis of the state of the epithelium posterius (endothelium) in the human eye cornea. As initial data, we used (respectively) (1) images of imprints of the eyelid intermarginal space on a millipore filter upon their osmium vapor staining; (2) micrographs of corneal tissue specimens obtained using a light microscope; (3) fluorescent angiograms of the human fundus; and (4) images of endothelial cells obtained noninvasively using a confocal microscope. The developed methods are designed to extract morphometric data from these images. For each problem, the following results were obtained: (1) expectations and variances of pixel intensities on the imprint along a drawn line and over a selected region, as well as plots that characterize pixel intensity and change in the thickness of the imprint along a drawn line; (2) expectations and variances for the intensities of the selected regions and intensity histograms; (3) extracted vessels and ischemia zones with their statistical descriptions; and (4) detected cells of hexagonal, pentagonal, and other shapes, as well as a set of characteristics associated with the size of the cells detected. The developed methods are based on the fundamental results of the mathematical theory of image analysis and on the joint use of image processing, mathematical morphology, and mathematical statistics techniques. The paper also describes software implementations of the developed methods, including an automated research workstation for ophthalmologists, and presents the results of their experimental testing.

Pattern Recognition and Image Analysis. 2018;28(4):612-636
pages 612-636 views

Methods of Intellectual Analysis in Medical Diagnostic Tasks Using Smart Feature Selection

Ilyasova N.Y., Shirokanev A.S., Kupriyanov A.V., Paringev R.A., Kirsh D.V., Soifer A.V.

Abstract

The paper deals with a computer technique for high-performance processing, analysis and interpretation of medical and diagnostic images. We propose a new approach to the analysis of different classes of images based on evaluation of aggregate geometric and texture parameters of allocated regions of interest which are supposed to be a basic feature set. The developed efficient feature-space generation technique is based on Big Data mining of unstructured information by applying the discriminative analysis methods. The technique makes it possible to extract regions of interest on fundus images containing four classes of objects: exudates, intact areas, thick vessels, and thin vessels. The use of Big Data technology made it possible, due to involving large amounts of data, to improve the training sample and reduce classification errors that ensured an increase of diagnosis accuracy up to 95%. The proposed technique has been applied to the coagulate location problem, that is a crucial problem of diabetic retinopathy treatment. The experiment results on real eye fundus images proved a considerable increase of treatment effectiveness.

Pattern Recognition and Image Analysis. 2018;28(4):637-645
pages 637-645 views

Approximation-Based Transformation of Color Signal for Heart Rate Estimation with a Webcam

Kopeliovich M., Petrushan M., Shaposhnikov D.

Abstract

Photoplethysmography (PPG) is a method for contactless heart rate estimation through the analysis of slight variations of skin color. Skin color variation caused by changes in the blood volume in vessels and registered by a camera is called color signal. Recent studies proved that some PPG methods could be used to produce accurate heart rate estimations on videodata recorded by common web-cameras that makes them potentially applicable for longterm health monitoring in home or office conditions. In this work, we study novel Approximation-based transformation method of signal processing and evaluate its combination with common preprocessing and postprocessing algorithms. Approximation-based transformation is the procedure of computing an approximation signal that consists of leading coefficients of the local quadratic approximation of the color signal.

Pattern Recognition and Image Analysis. 2018;28(4):646-651
pages 646-651 views

Iris Segmentation in Challenging Conditions

Korobkin M., Odinokikh G., Efimov Y., Solomatin I., Matveev I.

Abstract

Iris segmentation is an irreplaceable stage of iris recognition pipeline. Its quality hugely affects overall accuracy. Previously when conditions were mild and controlled the task was solved by image processing techniques and rule based approaches. Nowadays widespread of biometric technologies has relaxed operation conditions for such systems demanding more flexible and robust solutions. Constantly increasing data and sensors availability created fertile field for growth of machine learning methods capable to cope with complex conditions. The latest contributions to iris segmentation were made on this surge by leveraging abundant data and modern machine learning algorithms. In spite of previously achieved great results this work addresses even more challenging conditions that allows iris recognition to be used in wide range of real life cases. Novel CNN architectures are proposed in this work. They were designed to combine the latest achievements in classification and semantic segmentation fields. FCN and SegNet architectures have been picked up as prototypes and were strengthened by residual blocks. This allowed to make lightweight networks that could be shipped on various embedded platforms to successfully operate under less controllable environmental conditions. The approach allowed to obtain 0.93 and 0.92 IoU on original and modified CASIA-Iris-Lamp datasets which is a significant improvement in comparison with the results achieved before.

Pattern Recognition and Image Analysis. 2018;28(4):652-657
pages 652-657 views

In Defense of Active Part Selection for Fine-Grained Classification

Korsch D., Denzler J.

Abstract

Fine-grained classification is a recognition task where subtle differences distinguish between different classes. To tackle this classification problem, part-based classification methods are mostly used. Partbased methods learn an algorithm to detect parts of the observed object and extract local part features for the detected part regions. In this paper we show that not all extracted part features are always useful for the classification. Furthermore, given a part selection algorithm that actively selects parts for the classification we estimate the upper bound for the fine-grained recognition performance. This upper bound lies way above the current state-of-the-art recognition performances which shows the need for such an active part selection method. Though we do not present such an active part selection algorithm in this work, we propose a novel method that is required by active part selection and enables sequential part-based classification. This method uses a support vector machine (SVM) ensemble and allows to classify an image based on arbitrary number of part features. Additionally, the training time of our method does not increase with the amount of possible part features. This fact allows to extend the SVM ensemble with an active part selection component that operates on a large amount of part feature proposals without suffering from increasing training time.

Pattern Recognition and Image Analysis. 2018;28(4):658-663
pages 658-663 views

Shape of Basic Clusters: Using Analogues of Hough Transform in Higher Dimensions

Laptin Y.P., Nelyubina E.A., Ryazanov V.V., Vinogradov A.P.

Abstract

A new unified method for improving a wide class of linear decision rules is proposed on the basis of using the concept of Generalized Precedent and analogues of Hough transform in higher dimensions.

Pattern Recognition and Image Analysis. 2018;28(4):664-669
pages 664-669 views

Iris Anti-Spoofing Solution for Mobile Biometric Applications

Odinokikh G., Efimov I., Solomatin I., Korobkin M., Matveev I.

Abstract

The ability to provide reliable protection against counterfeiting is one of the key requirements for a biometric security system. Iris recognition as the technology emerging on mobile market is assumed to handle various types of spoof attacks to prevent compromise of the user’s personal data. A method of iris anti-spoofing is proposed in this work. It is based on applying of convolutional neural network and capable to work in real-time on the mobile device with highly limited computational resources. Classification of iris sample for spoof and live is made by a single frame using a pair of images: eye region and normalized iris. The following types of iris spoof samples are considered in this particular work: printed on paper, printed on paper with imposition of a contact lens, printed on paper with application of transparent glue. Testing of the method is performed on the dataset manually collected and containing all the mentioned spoof sample types. The method revealed its high performance in both classification accuracy and processing speed as well as robustness under uncontrollably changing environmental conditions, which are specific and significant when interacting with the mobile device.

Pattern Recognition and Image Analysis. 2018;28(4):670-675
pages 670-675 views

Dataless Black-Box Model Comparison

Theiss C., Brust C.A., Denzler J.

Abstract

In a time where the training of new machine learning models is extremely time-consuming and resource-intensive and the sale of these models or the access to them is more popular than ever, it is important to think about ways to ensure the protection of these models against theft. In this paper, we present a method for estimating the similarity or distance between two black-box models. Our approach does not depend on the knowledge about specific training data and therefore may be used to identify copies of or stolen machine learning models. It can also be applied to detect instances of license violations regarding the use of datasets. We validate our proposed method empirically on the CIFAR-10 and MNIST datasets using convolutional neural networks, generative adversarial networks and support vector machines. We show that it can clearly distinguish between models trained on different datasets. Theoretical foundations of our work are also given.

Pattern Recognition and Image Analysis. 2018;28(4):676-683
pages 676-683 views

Mathematical Method in Pattern Recognition

An Algorithm for Reselecting a Reference Objects

Bondarenko N.N.

Abstract

The problem of optimally choosing a learning object is studied. The definition of essential totality of precedents is given. It is shown that an iterative procedure for generating the essential totality of precedents exists. The algorithm operation is checked on model data.

Pattern Recognition and Image Analysis. 2018;28(4):684-687
pages 684-687 views

Method of Code Description of Classes for Solving Multi-Class Problem

Dokukin A.A.

Abstract

The method of code description of classes, which is a development of the ECOC (error-correcting output codes) method, is grounded theoretically. The main difference is as follows: a multiset of code descriptions of its training objects is used instead of one object code. It is shown that under certain conditions the two methods are equivalent. Ways for improving the recognition quality if code descriptions are used are shown.

Pattern Recognition and Image Analysis. 2018;28(4):688-694
pages 688-694 views

Structure Choice for Relations between Objects in Metric Classification Algorithms

Ignatyev N.A.

Abstract

We analyze the cluster structure of learning samples, decomposing class objects into disjoint groups. Decomposition results are used for the computation of the compactness measure for the sample and its minimal coverage by standard objects. We show that the number of standard objects depends on the metric choice, the distance to noise objects, the scales of the feature measurements, and nonlinear transformations of the feature space. We experimentally prove that the set of standards of the minimal coverage and noise objects affect the algorithm generalizing ability.

Pattern Recognition and Image Analysis. 2018;28(4):695-702
pages 695-702 views

An Exact Algorithm of Searching for the Largest Cluster in an Integer-Valued Problem of 2-Partitioning a Sequence

Kel’manov A.V., Khamidullin S.A., Khandeev V.I., Pyatkin A.V.

Abstract

We analyze mathematical aspects of one of the fundamental data analysis problems consisting in the search (selection) for the subset with the largest number of similar elements among a collection of objects. In particular, the problem appears in connection with the analysis of data in the form of time series (discrete signals). One of the problems in modeling this challenge is considered, namely, the problem of finding the cluster of the largest size (cardinality) in a 2-partition of a finite sequence of points in Euclidean space into two clusters (subsequences) under two constraints. The first constraint is on the choice of the indices of elements included in the clusters. This constraint simulates the set of time-admissible configurations of similar elements in the observed discrete signal. The second constraint is imposed on the value of the quadratic clustering function. This constraint simulates the level of intracluster proximity of objects. The clustering function under the second constraint is the sum (over both clusters) of the intracluster sums of squared distances between the cluster elements and its center. The center of one of the clusters is unknown and defined as the centroid (the arithmetic mean over all elements of this cluster). The center of the other cluster is the origin. Under the first constraint, the difference between any two subsequent indices of elements contained in a cluster with an unknown center is bounded above and below by some constants. It is established in the paper that the optimization problem under consideration, which models one of the simplest significant problems of data analysis, is strongly NP-hard. We propose an exact algorithm for the case of a problem with integer coordinates of its input points. If the dimension of the space is bounded by a constant, then the algorithm is pseudopolynomial.

Pattern Recognition and Image Analysis. 2018;28(4):703-711
pages 703-711 views

Multidimensional Data Visualization Based on the Minimum Distance Between Convex Hulls of Classes

Nemirko A.P.

Abstract

The problem of data visualization in the analysis of two classes in a multidimensional feature space is considered. The two orthogonal axes by which the classes are maximally separated from each other are found in the mapping of classes as a result of linear transformation of coordinates. The proximity of the classes is estimated based on the minimum-distance criterion between their convex hulls. This criterion makes it possible to show cases of full class separability and random outliers. A support vector machine is used to obtain orthogonal vectors of the reduced space. This method ensures the obtaining of the weight vector that determines the minimum distance between the convex hulls of classes for linearly separable classes. Algorithms with reduction, contraction, and offset of convex hulls are used for intersecting classes. Experimental studies are devoted to the application of the considered visualization methods to biomedical data analysis.

Pattern Recognition and Image Analysis. 2018;28(4):712-719
pages 712-719 views

On Some Transformations of Features in Machine Learning in Medicine

Zhuravlev Y.I., Ryazanov V.V., Sen’ko O.V., Dokukin A.A., Afanas’ev P.A.

Abstract

A new view is given to supervised classification problems by precedents on the basis of logical approaches and the possibility of their application in medicine. The basic logical and logical statistical models of classification (basic definitions, search, processing, and application of logical regularities of classes (LRCs); transition to other feature spaces; and the method of optimal reliable decompositions) and their verification are presented. Numerous applications in medicine and two problems of qualification assessment and choice of the treatment method are considered.

Pattern Recognition and Image Analysis. 2018;28(4):720-736
pages 720-736 views

Representation, Processing, Analysis, and Understanding of Images

On Recognition of Graphs and Images

Leontiev V.K., Gordeev E.N.

Abstract

This paper discusses the possibility of using the classical results of graph theory related to reconstruction and recognition of graphs and their characteristics in the field of image recognition. Two heuristic approaches are proposed to estimate the adequacy of object images. Various aspects of the problem of graph description (representation) with the use of graph invariants are analyzed. New classes of invariants that can be used to construct the heuristics mentioned above are introduced and investigated. In addition, some statements concerning two aspects of the problem—the formation of complex invariants taking into account the basic and functional dependences among invariants—are proved.

Pattern Recognition and Image Analysis. 2018;28(4):737-746
pages 737-746 views

Variance Based Brightness Preserved Dynamic Histogram Equalization for Image Contrast Enhancement

Dhal K.G., Das A., Ghoshal N., Das S.

Abstract

This paper proposes a novel variant of Brightness Preserving Dynamic Histogram Equalization (BPDHE) having more brightness preserving capability with less computational time. This variant, called Variance based Brightness Preserve Dynamic Histogram Equalization (VBBPDHE) uses the interclass and intraclass variance information to segment out the histogram recursively. This variant does not need the smoothing operation of input histogram and also no need to compute local maxima or minima to segment out the histogram unlike BPDHE. Visual analysis, quality metrics and execution time clearly demonstrate the efficiency of the proposed VBBPDHE over well-known existing methods.

Pattern Recognition and Image Analysis. 2018;28(4):747-757
pages 747-757 views

Applied Problems

A Face Recognition Based Biometric Solution in Education

El Moutaouakil K., Satori K., Dahmouni A., Aharrane N.

Abstract

In last years, several biometric modalities are coming back into the field of education. Especially, face recognition modality that allows authenticating humans based on their facial features. The main objective of this paper is to implement the recognition system part for a global software that is intended to be used in many applications related to the educational field. Therefore, we propose to combine the face description method based on Local Gradient Probabilistic Pattern (LGPP), the two dimensional subspace methods, and machine learning classifiers. Firstly, we extract principal face component using the LGPP descriptor. Then, 2DDWT, 2DPCA, and 2DLDA subspace methods were implemented to reduce face features. Finally, support vector machine (SVM) and artificial neural network (ANN) based machine learning algorithms are applied to classify the set of the final features vectors. The experimental results on relevant databases demonstrate the effectiveness of the proposed system.

Pattern Recognition and Image Analysis. 2018;28(4):758-770
pages 758-770 views

Relevance of a Set of Topical Texts to a Knowledge Unit and the Estimation of the Closeness of Linguistic Forms of Its Expression to a Semantic Pattern

Emelyanov G.M., Mikhailov D.V., Kozlov A.P.

Abstract

Interrelated problems of completeness of knowledge extraction from a set (corpus) of subject-oriented texts are analyzed through the relevance to a source phrase and the search for the most rational linguistic variant of the description of a selected knowledge fragment. These problems are topical for constructing systems of information processing, analysis, estimation, and understanding. In addition, the basis for extracting image components of a source phrase is the joint estimation of the coupling strength of its word combinations encountered in the phrases of a text analyzed, and the splitting of these words into classes by the value of the TF-IDF metric relative to the corpus texts. The relevance of a text corpus to a source knowledge unit by the degree of covering the words of a source phrase with the most relevant sets of relations relative to documents in which its image components are represented most fully is introduced by expanding word relations to three and more elements (using the base of known syntactic relations and without using it). This estimation is proposed for the targeted selection of text-corpus phrases that are either mutually equivalent or semantically complementary to each other and represent the same image. To rank the selected phrases by the degree of closeness to a semantic pattern (i.e. sense standard), three alternative estimations are introduced: based on splitting the source-phrase words into classes by the meaning of the TF-IDF metric and based on the numerical estimation of their binding strength (considering prepositions and conjunctions and without them). In addition, the text information necessary to represent a selected knowledge unit is compressed at least two times preserving its meaning.

Pattern Recognition and Image Analysis. 2018;28(4):771-782
pages 771-782 views

Software Tools for Statistical Analysis of Some Precipitation Characteristics

Gorshenin A.K.

Abstract

The paper presents the design and implementation of software tools for statistical analysis of the real data based on the assumptions that empirical distribution can be approximated by generalized negative binomial (GNB) or generalized gamma (GG) families. Models based on GG distributions are widely applied in such practical problems as processing of synthetic-aperture radar images and speech signals, hydrological analysis and optical communications. In this paper, the GNB distributions are considered as a mixed Poisson law with the mixing GG distribution. This family could provide better fit with the different statistical data than classical negative binomial distributions that have been successfully used for analysis of precipitation events earlier. The parameter estimation is implemented using a functional approach, so approximations by different types of distributions are compared in sense of different metrics. The results of application of the implemented software tools are demonstrated on the example of the Potsdam precipitation events.

Pattern Recognition and Image Analysis. 2018;28(4):783-791
pages 783-791 views

Novel and Efficient Approach for Automated Separation, Segmentation, and Detection of Overlapped Elliptical Red Blood Cells

Abu-Qasmieh I.

Abstract

Shape recognition is considered as one of the challenges in automated digital image analysis and computer vision. One of the most commonly used shapes is the ellipse which is of great importance for many industrial and biomedical applications. In this study, a novel technique is proposed for segmenting and separating of overlapped elliptical shape objects using concavity analysis and several morphological image processing techniques. A comparative study of the detection speed and accuracy of elliptical objects between Iterative Random Hough Transformation (IRHT) algorithm approach and Direct Least Squares Fitting (DLSF) of Ellipses method has shown the great superiority of DLSF in both the speed and accuracy of recognition. The validation of the proposed techniques for segmentation and detection along with calculation of the efficiency of the system has shown those techniques to be robust and effective for automation of synthetic and real elliptical shapes. The red blood cells (RBCs) microscopic images of the blood smear in Hereditary Elliptocytosis disorder is studied as real elliptical shapes and a quantitative analysis was implemented on the detected RBCs, where the distribution parameters of the ellipse size (area), Roundness, Eccentricity, and Ellipticity are estimated in addition to RBCs counting. The proposed detection approach is successful in building a fully autonomous and accurate system with ellipse analysis capabilities.

Pattern Recognition and Image Analysis. 2018;28(4):792-804
pages 792-804 views

Detection of Wildfires along Transmission Lines Using Deep Time and Space Features

Yuan J., Wang L., Wu P., Gao C., Sun L.

Abstract

Traditional wildfire detection methods are of low efficiency and cannot meet user needs, a novel method based on deep time and space features along transmission line is proposed in this paper, which uses ViBe algorithm to detect movements in videos, and extracts static deep feature in the space domain and dynamic optical flow feature in the time domain respectively. At last the deep convolutional neural network model in cascade is used to classify and find out real wildfire regions. By using combined deep features extracted from dynamic time-domain and static space-domain respectively, our method can eliminate the interference of movements of other objects with similar colors.

Pattern Recognition and Image Analysis. 2018;28(4):805-812
pages 805-812 views

An Adaptive Entropy Based Scale Invariant Face Recognition Face Altered by Plastic Surgery

Sable A.H., Talbar S.N.

Abstract

Face recognition is one of the challenging problems which suffer from practical issues like the pose, expression, illumination changes, and aging. Plastic surgery is one among the issues that pose great difficulty in recognizing the faces. The literature has been reported with traditional features and classifiers for recognizing the faces after plastic surgery. This paper presents an adaptive feature descriptor and advanced classifier for plastic surgery face recognition. According to the proposed feature descriptor, firstly an adaptive Gaussian transfer function is determined to perform Adaptive Gaussian Filtering (AGF) for images. Secondly, Adaptive Entropy-based SIFT (AEV-SIFT) features are extracted from the filtered images. Unlike traditional SIFT, the proposed AEV-SIFT extracts the key points based on the entropy of the volume information of the pixel intensities. This provides the least effect on uncertain variations in the face because the entropy is the higher order statistical feature. Further, the classification is performed with variations. In the first variation, support vector machine (SVM) is used as a classifier, whereas the second variation exploits the Deep Learning Network (DLN) for recognizing the faces based on the AEV-SIFT features. The proposed method classifies the plastic surgery face images with the accuracy of 80.15%, sensitivity of 19.75% and specificity of 95%, which are obviously better than the traditional features such as SIFT, V-SIFT, and Principal Component Analysis (PCA).

Pattern Recognition and Image Analysis. 2018;28(4):813-829
pages 813-829 views

Method of Estimating the Geometric Parameters of a Three-Dimensional Object from Resistivity Survey Data

Zhurbin I.V., Nemtsova O.M., Zlobina A.G., Gruzdev D.V.

Abstract

The testing of the proposed method for estimating the geometric parameters of a three-dimensional object from the data of computer-aided simulation and field experiments confirmed by excavation provide the possibility to determine the location of anomalous-resistance objects under the ground and to perform the quantitative estimation of their geometric parameters (shape, dimensions, and burial depth) from resistivity survey data. It is shown that the analysis of the vector pictures of main resistance change directions provides the possibility to estimate the spatial location of an object of search (along the depth and in horizontal “sections”) at a qualitative level and to determine its relative resistance. The application of the scalar product function and the adaptive fuzzy clustering algorithm to these vector pictures provides the possibility to estimate the shape of an object of search and the range of its burial depths. Using the A* optimal path search algorithm, it is possible to plot the boundary line of an object on a set of horizontal “sections.”

Pattern Recognition and Image Analysis. 2018;28(4):830-840
pages 830-840 views