Pub Date : 2019-01-01DOI: 10.18287/1613-0073-2019-2391-79-85
N. Andriyanov, M. N. Sluzhivyi
When describing a real image using a mathematical model, the problem of model parameters identification is of importance. In this case the identification itself is easier to perform when a particular type of model is known. In other words, if there is a number of models characterized by different properties, then if there is a correspondence with the type of suitable images, then the model to be used can be determined in advance. Therefore, in this paper, we do not consider the criteria for model selection, but perform the identification of parameters for autoregressive models, including those with multiple roots of characteristic equations. This is due to the fact that the effectiveness of identification is verified by the images generated by this model. However, even using this approach where the model is known, one must first determine the order of the model. In this regard, on the basis of YuleWalker equations, an algorithm for determining the order of the model is investigated, and the optimal parameters of the model are also found. In this case the proposed algorithm can be used when processing real images.
{"title":"Solution for the problem of the parameters identification for autoregressions with multiple roots of characteristic equations","authors":"N. Andriyanov, M. N. Sluzhivyi","doi":"10.18287/1613-0073-2019-2391-79-85","DOIUrl":"https://doi.org/10.18287/1613-0073-2019-2391-79-85","url":null,"abstract":"When describing a real image using a mathematical model, the problem of model parameters identification is of importance. In this case the identification itself is easier to perform when a particular type of model is known. In other words, if there is a number of models characterized by different properties, then if there is a correspondence with the type of suitable images, then the model to be used can be determined in advance. Therefore, in this paper, we do not consider the criteria for model selection, but perform the identification of parameters for autoregressive models, including those with multiple roots of characteristic equations. This is due to the fact that the effectiveness of identification is verified by the images generated by this model. However, even using this approach where the model is known, one must first determine the order of the model. In this regard, on the basis of YuleWalker equations, an algorithm for determining the order of the model is investigated, and the optimal parameters of the model are also found. In this case the proposed algorithm can be used when processing real images.","PeriodicalId":10486,"journal":{"name":"Collection of selected papers of the III International Conference on Information Technology and Nanotechnology","volume":"32 1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89537449","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-01-01DOI: 10.18287/1613-0073-2019-2416-534-541
M. P. Osipov, O. A. Chekodaev
The paper presents methods for optimizing the process of visualization of the urban environment model based on the characteristics of its presentation. Various approaches are described which provide a reduction in computational complexity in visualizing threedimensional models that can optimize the display of their geometry and the amount of video memory used. Methods are considered that allow optimizing both the scene as a whole and its individual components.
{"title":"Optimization of the process of 3D visualization of the model of urban environment objects generated on the basis of the attributive information from a digital map","authors":"M. P. Osipov, O. A. Chekodaev","doi":"10.18287/1613-0073-2019-2416-534-541","DOIUrl":"https://doi.org/10.18287/1613-0073-2019-2416-534-541","url":null,"abstract":"The paper presents methods for optimizing the process of visualization of the urban environment model based on the characteristics of its presentation. Various approaches are described which provide a reduction in computational complexity in visualizing threedimensional models that can optimize the display of their geometry and the amount of video memory used. Methods are considered that allow optimizing both the scene as a whole and its individual components.","PeriodicalId":10486,"journal":{"name":"Collection of selected papers of the III International Conference on Information Technology and Nanotechnology","volume":"243 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91435226","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-01-01DOI: 10.18287/1613-0073-2019-2416-340-353
M. Bulygin, M. Gayanova, A. M. Vulfin, A. Kirillova, R. Gayanov
Object of the research are modern structures and architectures of neural networks for image processing. Goal of the work is improving the existing image processing algorithms based on the extraction and compression of features using neural networks using the colorization of black and white images as an example. The subject of the work is the algorithms of neural network image processing using heterogeneous convolutional networks in the colorization problem. The analysis of image processing algorithms with the help of neural networks is carried out, the structure of the neural network processing system for image colorization is developed, colorization algorithms are developed and implemented. To analyze the proposed algorithms, a computational experiment was conducted and conclusions were drawn about the advantages and disadvantages of each of the algorithms.
{"title":"Convolutional neural network in the images colorization problem","authors":"M. Bulygin, M. Gayanova, A. M. Vulfin, A. Kirillova, R. Gayanov","doi":"10.18287/1613-0073-2019-2416-340-353","DOIUrl":"https://doi.org/10.18287/1613-0073-2019-2416-340-353","url":null,"abstract":"Object of the research are modern structures and architectures of neural networks for image processing. Goal of the work is improving the existing image processing algorithms based on the extraction and compression of features using neural networks using the colorization of black and white images as an example. The subject of the work is the algorithms of neural network image processing using heterogeneous convolutional networks in the colorization problem. The analysis of image processing algorithms with the help of neural networks is carried out, the structure of the neural network processing system for image colorization is developed, colorization algorithms are developed and implemented. To analyze the proposed algorithms, a computational experiment was conducted and conclusions were drawn about the advantages and disadvantages of each of the algorithms.","PeriodicalId":10486,"journal":{"name":"Collection of selected papers of the III International Conference on Information Technology and Nanotechnology","volume":"21 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75404798","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-01-01DOI: 10.18287/1613-0073-2019-2416-199-203
S. Vostokin, I. Bobyleva
The article discusses the application of the bag of tasks programming model for the problem of sorting a large data array. The choice is determined by the generality of its algorithmic structure with various problems from the field of data analysis including correlation analysis, frequency analysis, and data indexation. The sorting algorithm is a blockby-block sorting, followed by the pairwise merging of the blocks. At the end of the sorting, the data in the blocks form an ordered sequence. The order of sorting and merging tasks is set by a static directed acyclic graph. The sorting algorithm is implemented using MPI library in C ++ language with centralized storing of data blocks on the manager process. A feature of the implementation is the transfer of blocks between the master and the worker MPI processes for each task. Experimental study confirmed the hypothesis that the intensive data exchange resulting from the centralized nature of the bag of task model does not lead to a loss of performance. The data processing model makes it possible to weaken the technical requirements for the software and hardware.
{"title":"Using the bag-of-tasks model with centralized storage for distributed sorting of large data array","authors":"S. Vostokin, I. Bobyleva","doi":"10.18287/1613-0073-2019-2416-199-203","DOIUrl":"https://doi.org/10.18287/1613-0073-2019-2416-199-203","url":null,"abstract":"The article discusses the application of the bag of tasks programming model for the problem of sorting a large data array. The choice is determined by the generality of its algorithmic structure with various problems from the field of data analysis including correlation analysis, frequency analysis, and data indexation. The sorting algorithm is a blockby-block sorting, followed by the pairwise merging of the blocks. At the end of the sorting, the data in the blocks form an ordered sequence. The order of sorting and merging tasks is set by a static directed acyclic graph. The sorting algorithm is implemented using MPI library in C ++ language with centralized storing of data blocks on the manager process. A feature of the implementation is the transfer of blocks between the master and the worker MPI processes for each task. Experimental study confirmed the hypothesis that the intensive data exchange resulting from the centralized nature of the bag of task model does not lead to a loss of performance. The data processing model makes it possible to weaken the technical requirements for the software and hardware.","PeriodicalId":10486,"journal":{"name":"Collection of selected papers of the III International Conference on Information Technology and Nanotechnology","volume":"210 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76210087","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-01-01DOI: 10.18287/1613-0073-2019-2391-48-53
L. Shiripova, E. Myasnikov
The paper is devoted to the problem of recognizing human actions in videos recorded in the optical range of wavelengths. An approach proposed in this paper consists in the detection of a moving person on a video sequence with the subsequent size normalization, generation of subsequences and dimensionality reduction using the principal component analysis technique. The classification of human actions is carried out using a support vector machine classifier. Experimental studies performed on the Weizmann dataset allowed us to determine the best values of the method parameters. The results showed that with a small number of action classes, high classification accuracy can be achieved.
{"title":"Human action recognition using dimensionality reduction and support vector machine","authors":"L. Shiripova, E. Myasnikov","doi":"10.18287/1613-0073-2019-2391-48-53","DOIUrl":"https://doi.org/10.18287/1613-0073-2019-2391-48-53","url":null,"abstract":"The paper is devoted to the problem of recognizing human actions in videos recorded in the optical range of wavelengths. An approach proposed in this paper consists in the detection of a moving person on a video sequence with the subsequent size normalization, generation of subsequences and dimensionality reduction using the principal component analysis technique. The classification of human actions is carried out using a support vector machine classifier. Experimental studies performed on the Weizmann dataset allowed us to determine the best values of the method parameters. The results showed that with a small number of action classes, high classification accuracy can be achieved.","PeriodicalId":10486,"journal":{"name":"Collection of selected papers of the III International Conference on Information Technology and Nanotechnology","volume":"16 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79308307","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-01-01DOI: 10.18287/1613-0073-2019-2391-114-120
A. Tashlinskii, A. Zhukova, D. Kraus
Several approaches to the numerical description of image inter-frame geometric deformations parameters estimates behavior at iterations of non-identification relay stochastic gradient estimation are considered. The probability density of the Euclidean mismatch distance of estimates vector is chosen as an argument of the characteristics forming the numerical values. It made it possible to ensure invariance of research to the set of parameters of the used inter-frame geometric deformations model. The mathematical expectation, the probability of exceeding a given threshold value of the convergence rate and the confidence interval of the Euclidean mismatch distance were investigated as characteristics. Probabilistic mathematical modeling is applied to calculate the probability density of the Euclidean mismatch distance.
{"title":"Convergence characteristics at stochastic estimation of image inter-frame deformations","authors":"A. Tashlinskii, A. Zhukova, D. Kraus","doi":"10.18287/1613-0073-2019-2391-114-120","DOIUrl":"https://doi.org/10.18287/1613-0073-2019-2391-114-120","url":null,"abstract":"Several approaches to the numerical description of image inter-frame geometric deformations parameters estimates behavior at iterations of non-identification relay stochastic gradient estimation are considered. The probability density of the Euclidean mismatch distance of estimates vector is chosen as an argument of the characteristics forming the numerical values. It made it possible to ensure invariance of research to the set of parameters of the used inter-frame geometric deformations model. The mathematical expectation, the probability of exceeding a given threshold value of the convergence rate and the confidence interval of the Euclidean mismatch distance were investigated as characteristics. Probabilistic mathematical modeling is applied to calculate the probability density of the Euclidean mismatch distance.","PeriodicalId":10486,"journal":{"name":"Collection of selected papers of the III International Conference on Information Technology and Nanotechnology","volume":"2400 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86573498","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-01-01DOI: 10.18287/1613-0073-2019-2416-87-94
M. Bolotov, V. Pechenin, N. V. Ruzanov, D. Balyakin
The quality of aircraft and rocket engines depends primarily on the geometric accuracy of assembly units and parts. Mathematical models implemented in the form of computer models are used to predict quality indicators (in particular, assembly parameters). Direct modeling of the conjugation process using numerical conjugation and finite-element models of assemblies requires significant computational resources and is often accompanied by problems convergence of solutions. In order to solve the above problems, it is possible to use neural network models describing the main regularities of the pairing process based on the accumulated results. The work presents a neural network model for predicting assembly parameters of the parts based on the use of actual surfaces of the parts obtained as a result of mathematical modeling. Assembly on conical surfaces is considered. A convolutional neural network was used to predict assembly parameters.
{"title":"Neural network model in digital prediction of geometric parameters for relative position of the aircraft engine parts","authors":"M. Bolotov, V. Pechenin, N. V. Ruzanov, D. Balyakin","doi":"10.18287/1613-0073-2019-2416-87-94","DOIUrl":"https://doi.org/10.18287/1613-0073-2019-2416-87-94","url":null,"abstract":"The quality of aircraft and rocket engines depends primarily on the geometric accuracy of assembly units and parts. Mathematical models implemented in the form of computer models are used to predict quality indicators (in particular, assembly parameters). Direct modeling of the conjugation process using numerical conjugation and finite-element models of assemblies requires significant computational resources and is often accompanied by problems convergence of solutions. In order to solve the above problems, it is possible to use neural network models describing the main regularities of the pairing process based on the accumulated results. The work presents a neural network model for predicting assembly parameters of the parts based on the use of actual surfaces of the parts obtained as a result of mathematical modeling. Assembly on conical surfaces is considered. A convolutional neural network was used to predict assembly parameters.","PeriodicalId":10486,"journal":{"name":"Collection of selected papers of the III International Conference on Information Technology and Nanotechnology","volume":"9 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86337640","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-01-01DOI: 10.18287/1613-0073-2019-2391-350-357
E. Medvedeva, A. Evdokimova
The authors offer a method for detecting the edges of texture objects in remote sensing images. This method is based on the evaluation of textural and brightness attributes. It is proposed to use transition probabilities for three-dimensional Markov chains with two states as texture features, averaged within a sliding window. It makes possible to improve the detection accuracy of texture objects on multichannel or multi-time snapshots. To reduce the computational resources, it is proposed to determine the signs by the bit planes of the senior, most informative digits of the digital image. The simulation results confirm the effectiveness of the proposed method.
{"title":"Improving the accuracy of detecting the edges of texture objects in remote sensing images","authors":"E. Medvedeva, A. Evdokimova","doi":"10.18287/1613-0073-2019-2391-350-357","DOIUrl":"https://doi.org/10.18287/1613-0073-2019-2391-350-357","url":null,"abstract":"The authors offer a method for detecting the edges of texture objects in remote sensing images. This method is based on the evaluation of textural and brightness attributes. It is proposed to use transition probabilities for three-dimensional Markov chains with two states as texture features, averaged within a sliding window. It makes possible to improve the detection accuracy of texture objects on multichannel or multi-time snapshots. To reduce the computational resources, it is proposed to determine the signs by the bit planes of the senior, most informative digits of the digital image. The simulation results confirm the effectiveness of the proposed method.","PeriodicalId":10486,"journal":{"name":"Collection of selected papers of the III International Conference on Information Technology and Nanotechnology","volume":"37 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78051573","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-01-01DOI: 10.18287/1613-0073-2019-2391-243-249
A. Kovalenko, Y. Demyanenko
This paper describes an approach to solving the problem of finding similar images by visual similarity using neural networks on previously unmarked data. We propose to build special architecture of the neural network - autoencoder, through which high-level features are extracted from images. The search for the nearest elements is realized by the Euclidean metric in the generated feature space, after a preliminary decomposition into two-dimensional space. Proposed approach of generate feature space can be applied to the classification task using pre-clustering.
{"title":"Image clustering by autoencoders","authors":"A. Kovalenko, Y. Demyanenko","doi":"10.18287/1613-0073-2019-2391-243-249","DOIUrl":"https://doi.org/10.18287/1613-0073-2019-2391-243-249","url":null,"abstract":"This paper describes an approach to solving the problem of finding similar images by visual similarity using neural networks on previously unmarked data. We propose to build special architecture of the neural network - autoencoder, through which high-level features are extracted from images. The search for the nearest elements is realized by the Euclidean metric in the generated feature space, after a preliminary decomposition into two-dimensional space. Proposed approach of generate feature space can be applied to the classification task using pre-clustering.","PeriodicalId":10486,"journal":{"name":"Collection of selected papers of the III International Conference on Information Technology and Nanotechnology","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88786443","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-01-01DOI: 10.18287/1613-0073-2019-2391-326-333
A. V. Goncharova, I. Safonov, I. Romanov
In the paper, we propose an approach for selection a correction parameter for images damaged by backlighting. We consider the photos containing underexposed areas due to backlit conditions. Such areas are dark and have poorly discernible details. The correction parameter controls the level of amplification of local contrast in shadow tones. Besides, the correction parameter can be considered as a quality estimation factor for such photos. For an automatic selection of the correction parameter, we apply regression by supervised machine learning. We propose new features calculated from the co-occurrence matrix for the training of the regression model. We compare the performance of the following techniques: the least square method, support vector machine, random forest, CART, random forest, two shallow neural networks as well as blending and staking of several models. We apply two-stage approach for the collection of a big dataset for training: initial model is trained on a manually labeled dataset containing about two hundred of photos, after that we use the initial model for searching for photos damaged by backlit in social networks having public API. Such approach allowed to collect about 1000 photos in conjunction with their preliminary quality assessments that were corrected by experts if it was necessary. In addition, we investigate an application of several well-known blind quality metrics for the estimation of photos affected by backlit.
{"title":"The regression model for the procedure of correction of photos damaged by backlighting","authors":"A. V. Goncharova, I. Safonov, I. Romanov","doi":"10.18287/1613-0073-2019-2391-326-333","DOIUrl":"https://doi.org/10.18287/1613-0073-2019-2391-326-333","url":null,"abstract":"In the paper, we propose an approach for selection a correction parameter for images damaged by backlighting. We consider the photos containing underexposed areas due to backlit conditions. Such areas are dark and have poorly discernible details. The correction parameter controls the level of amplification of local contrast in shadow tones. Besides, the correction parameter can be considered as a quality estimation factor for such photos. For an automatic selection of the correction parameter, we apply regression by supervised machine learning. We propose new features calculated from the co-occurrence matrix for the training of the regression model. We compare the performance of the following techniques: the least square method, support vector machine, random forest, CART, random forest, two shallow neural networks as well as blending and staking of several models. We apply two-stage approach for the collection of a big dataset for training: initial model is trained on a manually labeled dataset containing about two hundred of photos, after that we use the initial model for searching for photos damaged by backlit in social networks having public API. Such approach allowed to collect about 1000 photos in conjunction with their preliminary quality assessments that were corrected by experts if it was necessary. In addition, we investigate an application of several well-known blind quality metrics for the estimation of photos affected by backlit.","PeriodicalId":10486,"journal":{"name":"Collection of selected papers of the III International Conference on Information Technology and Nanotechnology","volume":"32 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80039849","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：