ElAr :: Перегляд за автором "Gorokhovatskyi, V."

Перегляд за автором "Gorokhovatskyi, V."

Зараз показано 1 - 19 з 19

Accelerating Image Classification based on a Model for Estimating Descriptor-to-Class Distance
(2023) Gorokhovatskyi, V.; Gadetska, S.; Stiahlyk, N.
The article describes a method of image classification based on the estimation of the distance to the etalon class. The implementation of estimates gives a significant gain in classification speed compared to linear search while maintaining a decent level of accuracy. The methodology is based on the use of the triangle inequality for images given by a set of binary vectors as descriptors of the image key points. The evaluation is applied to the "object descriptor – etalon" classification method, which is based on the descriptor voting procedure. An analysis of evaluation options is carried out using the parameters of the etalon sets in the form of a medoid and the closest or farthest points from it. The gain in classification time compared to the traditional method proportionally depends on the number of descriptors in the etalon description. Software simulation of classifiers with the implementation of evaluation shows a gain in speed of 350-450 times for the description of 500 descriptors while maintaining one hundred percent classification accuracy on the training set of similar NFT images. A control sample experiment shows that the classifier with estimation can respond better to image details compared to the traditional method.
Aggregate Parametric Representation of Image Structural Description in Statistical Classification Methods
(2022) Gadetska, S.; Gorokhovatskyi, V.; Stiahlyk, N.; Vlasenko, N.
Finding effective classification solutions based on the study of the processed data nature is one of the important tasks in modern computer vision. Statistical distributions are a perfect tool for presenting and analyzing visual data in image recognition systems. They are especially effective when creating new feature spaces, particularly, by aggregating descriptor sets in some appropriate way, including bits. For this purpose, it is natural to apply the number of criteria designed to compare the distribution parameters of the analyzed samples. The article develops a speed-efficient method of image classification by introducing aggregate statistical features for the composition of the description components. The metric classifier is based on the use of statisticalcriteria to assess the significance of the classification decision. The developed classification method based on the aggregation of the feature image set is implemented; the workability of the proposed classifier is confirmed. On the examples of the application of variants ofthe method for the system of the real images features, its effectiveness was experimentally evaluated.
An effective method for transforming an image description into a compact vector for classification
(Publishing House «Caravela», 2024) Gorokhovatskyi, V.; Tvoroshenko, I.
The work develops method to solve a fundamental problem in computer vision: image recognition of visual objects. Based on the implementation of the distance matrix model, it was possible to form effective integrated features in the form of one-dimensional data distributions and vectors for the sum of the matrix columns, which reduced computational costs without losing the effectiveness of classification on the training data sample. The efficiency of image classification was experimentally evaluated using software modeling.
Analysis of Application of Cluster Descriptions in Space of Characteristic Image Features
(2018) Gorokhovatskyi, V.
Abstract: Structural image recognition method modifications in space of characteristic features for recognition of computer vision image dataset were investigated. Recognition performance boost is achieved with quantization (clustering) in the space of image characteristic features that form the pattern of the object. Due to the transformation of structural objects descriptions from a set representation to a vector form, the amount of computation might be reduced tens of times. The results of experiments on Leeds Butterfly dataset that confirmed the effectiveness of decision-making systems based on the proposed approach are shown.
Application of deep learning methods for recognizing and classifying culinary dishes in images
(International Journal of Academic and Applied Research, 2023) Tvoroshenko, I.; Gorokhovatskyi, V.; Kobylin, O.; Tvoroshenko, A.
The paper deals with the actual tasks of computer vision – recognition and classification of objects in images. Deep learning methods based on neural networks are proposed as an alternative to existing methods. A new approach for effective recognition and classification of culinary dishes in images has been developed, which involves the use of the capabilities of the TensorFlow deep learning library and the features of the Convolutional Neural Network. A software application for recognizing and classifying culinary dishes has been developed. Testing of the proposed tool showed that 7 complete epochs of model training provided 77% accuracy, which is a fairly good result, given that one of the main problems in recognizing culinary dishes is interclass similarity. The prospect of further research is to create subclasses for existing general classes of dishes.
Application of video data classification models using convolutional neural networks
(International Journal of Academic and Applied Research, 2023) Tvoroshenko, I.; Pomazan, V.; Gorokhovatskyi, V.; Kobylin, O.
This paper explores the classification of video data with convolutional neural networks. It discusses how convolutional neural network architecture can do this task with fastness and maximum efficiency. By analyzing the different convolutional neural network models model was proposed that showed great results in this video classification task. The strengths and weaknesses of the neural network model for video classification have been identified, and the prospects for further work have also been outlined.
Classification of Images Based on a System of Hierarchical Features
(2022) Daradkeh Yousef Ibrahim; Gorokhovatskyi, V.; Tvoroshenko, I.; Al-Dhaifallah Mujahed
The results of the development of the new fast-speed method of classification images using a structural approach are presented. The method is based on the system of hierarchical features, based on the bitwise data distribution for the set of descriptors of image description. The article also proposes the use of the spatial data processing apparatus, which simplifies and accelerates the classification process. Experiments have shown that the time of calculation of the relevance for two descriptions according to their distributions is about 1000 times less than for the traditional voting procedure, for which the sets of descriptors are compared. The introduction of the system of hierarchical features allows to further reduce the calculation time by 2–3 times while ensuring high efficiency of classification. The noise immunity of the method to additive noise has been experimentally studied. According to the results of the research, the marginal degree of the hierarchy of features for reliable classification with the standard deviation of noise less than 30 is the 8-bit distribution. Computing costs increase proportionally with decreasing bit distribution. The method can be used for application tasks where object identification time is critical.
Cluster representation of the structural description of images for effective classification
(Computers, Materials & Continua, 2022) Daradkeh Yousef Ibrahim; Gorokhovatskyi, V.; Tvoroshenko, I.; Zeghid, M.
The problem of image recognition in the computer vision systems is being studied. The results of the development of efficient classification methods, given the figure of processing speed, based on the analysis of the segment representation of the structural description in the form of a set of descriptors are provided. We propose three versions of the classifier according to the following principles: “object–etalon”, “object descriptor–etalon” and “vector description of the object–etalon”, which are not similar in level of integration of researched data analysis. The options for constructing clusters over the whole set of descriptions of the etalon database, separately for each of the etalons, as well as the optimal method to compare sets of segment centers for the etalons and object, are implemented. An experimental rating of the efficiency of the created classifiers in terms of productivity, processing time, and classification quality has been realized of the applied. The proposed methods classify the set of etalons without error. We have formed the inference about the efficiency of classification approaches based on segment centers. The time of image processing according to the developed methods is hundreds of times less than according to the traditional one, without reducing the accuracy.
Development of an application for recognizing emotions using convolutional neural networks
(International Journal of Academic Information Systems Research, 2023) Pomazan, V.; Tvoroshenko, I.; Gorokhovatskyi, V.
This paper explores the potential of using convolutional neural networks (CNN) for emotion recognition in marketing research of advertising. Discusses how CNN can be trained to accurately recognize emotions conveyed in advertisements and how this information can be used to gain insights into consumer behavior. By analyzing consumer emotions in response to different types of advertising, marketers can better tailor their advertising campaigns to elicit positive emotional responses and improve overall effectiveness. Overall, the paper demonstrates the potential of CNN-based emotion recognition as a valuable tool to optimize advertising strategies and improve consumer engagement.
Features of distance education in the field of computer science in Ukraine
(2021) Gorokhovatskyi, V.; Baryshnikova, P.
Handwritten character recognition models based on convolutional neural networks
(International Journal of Academic Engineering Research, 2023) Pomazan, V.; Tvoroshenko, I.; Gorokhovatskyi, V.
This paper explores the possibility of using various convolutional neural network models to recognize handwritten Arabic characters. It discusses which of the existing convolutional neural network models best suits this task. The results are analyzed based on which conclusions are drawn regarding the effectiveness or ineffectiveness of specific convolutional neural network models. The paper provides an analysis of the efficiency of convolutional neural network models for the task of recognizing handwritten Arabic characters.
Identification of visual objects by the search request
(Kyiv-Uzhorod, 2023) Gorokhovatskyi, V.; Tvoroshenko, I.
Image Classification Based on the Kohonen Network and the Data Space Modification
(2020) Gorokhovatskyi, V.; Tvoroshenko, I.
In this paper, we propose the solution of visual object recognition in computer vision problems using the classification of descriptors of image key points based on the training of Kohonen neural network on the description data of etalons images. According to the results of training within the set of etalons, the image classification method has been improved by defining a specific data space in the form of a statistical center for each etalon. We propose mathematical models for the bitwise analysis of multiple descriptors searching for the centers and the method for convolution of descriptions from multiple descriptors with the determining a posteriori probabilities for the system of bit centers. Methods of data space transformation of description bits are proposed for various options for Kohonen network training, processing and estimation of class centers. The software implementation of the changed classifier was performed as well as the processing time with different options for determining the space of training data was estimated. Experimental researches confirmed the high efficiency of classification preserving sufficient performance and the ability to use proposed methods in real-time applications.
Image structural classification technologies based on statistical analysis of descriptions in the form of bit descriptor set.
(2020) Gorokhovatskyi, V.; Gadetska, S.; Stiahlyk, N.
The problem of image recognition in computer vision systems is considered. We offer technologies for classifying visual objects using a statistical center based on a structural description of the image as a set of key point descriptors. The use of statistics for the bits of the description data helps to increase performance while providing sufficient classification performance. Results of experimental modeling and peculiarities of implementation of the developed approaches are discussed.
Statistical data analysis models for determining the relevance of structural image descriptions
(IEEE Access, 2023) Daradkeh Yousef Ibrahim; Gorokhovatskyi, V.; Tvoroshenko, I.; Gadetska, S.; Al-Dhaifallah Mujahed
The aim of the research is to improve the effectiveness of image recognition methods according to the description in the form of a set of keypoint descriptors. The focus is on increasing the speed of analysis and processing of description data while maintaining the required level of classification efficiency. The class of the image is provided as a description of the etalon. It is proposed to transform the description by implementing a statistical system of features for non-intersecting data fragments. The developed method is based on the aggregation of data distribution values within the description, the basis of which is the bit representation of the descriptors. Statistical features are calculated as the frequency of occurrence of the fixed value of a fragment on a set of description data and thus reflect the individual properties of images. Three main classifier models are analyzed: calculating the measure of data relevance in the form of distributions; assigning each of the descriptors to defined classes (voting); using the apparatus of statistical data analysis to decide on the significance of the difference between the distributions of the object and etalons. The results of software modeling of methods and calculations of statistical significance of differences based on distributions for training sets of images are represented. Using distributions instead of a set of descriptors increases the processing speed by hundreds of times, while the classification accuracy is maintained at a sufficient level and does not deteriorate compared to traditional voting.
The Application of Hybrid Intelligence Systems for Dynamic Data Analysis
(International Journal of Engineering and Information Systems, 2022) Tvoroshenko, I.; Gorokhovatskyi, V.
The paper presents the results of scientific research, which were carried out under the set goal and solve the urgent task of developing and improving methods, models, and information technologies for assessing the states of complex spatially distributed objects based on evolutionary interval fuzzy models. A hybrid model for evaluating spatially distributed objects is proposed, which integrates developed fuzzy color Petri nets, models of deterministic, stochastic, and fuzzy knowledge bases, and the logic of manifestation of their interaction. The development allows increasing the probability of making decisions while reducing the dimension of the model by expanding the color function and the function of displaying spatial data. Alternative methods and tools for operational analysis in information technologies for assessing the states of complex spatially distributed objects have been introduced. This made it possible to reduce the influence of the subjective factor on the assessment results and increase the reliability of decisions made while reducing the time spent.
The Research of Image Classification Methods Based on the Introducing Cluster Representation Parameters for the Structural Description
(Seventh Sense Research Group, 2021) Ahmad M. Ayaz; Gorokhovatskyi, V.; Tvoroshenko, I.; Vlasenko, N.; Mustafa Syed Khalid
The results of the development of high-speed methods for classifying images in computer vision systems using the description as a set of keypoints descriptors are presented. Classification methods based on the system of cluster centers parameters, which are independently constructed for etalon descriptors set, are researched. The competitive voting of the descriptors of object being recognized on a set of etalon centers is proposed. An optimal way of comparing the sets of cluster centers for an object and etalons is applied. Experimental estimation of the efficiency for the two presented classification methods in terms of computation time and classification accuracy based on the results of applied dataset processing are shown. Based on the research, a conclusion about the effectiveness of classification technologies using cluster centers for structural descriptions of images to ensure decision-making in real-time is made.
Tools for Fast Metric Data Search in Structural Methods for Image Classification
(IEEE Access, 2022-01-02) Daradkeh Yousef Ibrahim; Gorokhovatskyi, V.; Tvoroshenko, I.; Zeghid Medien
The article proposes a new classification method based on implementing the high-speed search tools for the indexed data structure created on the etalon set of features, which has significant advantages in processing speed compared to the traditional approaches. The classifier is represented as two-stage processing, where at the first stage the class for the separate object descriptor is determined, and at the second stage, the resulting class of the object is determined based on the obtained set of local solutions. The developed method is based on the preliminary construction of the indexed hash structures for the set of descriptors of the base of the etalon images. Implementing the hash representation allows for increasing the speed of identification or classification of visual objects. A comparative experiment with the traditional method of voting has been conducted, where the linear search for the nearest descriptor has been implemented for the identification without the use of prior creation of the indexed hash representation of the etalons. In the experiment, we have gained in processing speed for the developed method compared to the traditional over 10 times. The gain in processing speed increases proportionally with the number of the etalons and the number of the descriptors in the descriptions. The experiment has shown that the efficiency of the method can be enhanced by varying the values of its parameters and adapting to the properties of the data.
Transforming image descriptions as a set of descriptors to construct classification features
(Indonesian Journal of Electrical Engineering and Computer Science, 2024) Gorokhovatskyi, V.; Tvoroshenko, I.; Yakovleva Olena
The article develops methods to solve a fundamental problem in computer vision: image recognition of visual objects. The results of the research on the construction of modifications for the space of classification features based on the application of the transformation of the structural description through the decomposition in the orthogonal basis and the implementation of the distance matrix model between the components of the description are presented. The application of the system of orthogonal functions as an apparatus for the transformation of the description showed the possibility of a significant gain in the speed of processing while maintaining high indicators of classification accuracy and interference resistance. The synthesized feature systems’ effectiveness has been confirmed in terms of a significant increase in the rate of codes and a sufficient level of efficiency. An experimental example showed that the time spent calculating the relevance of descriptions according to their modified presentation is more than ten times shorter than for traditional metric approaches. The developed classification features can be used in applied tasks where the time of visual objects’ identification is critical.

Перегляд за автором "Gorokhovatskyi, V."

Результатів на сторінку

Варіанти сортування