scispace - formally typeset
Search or ask a question
Author

Zufar Kayumov

Bio: Zufar Kayumov is an academic researcher from Kazan Federal University. The author has contributed to research in topics: MNIST database & Artificial neural network. The author has an hindex of 2, co-authored 6 publications receiving 13 citations.

Papers
More filters
Journal ArticleDOI
TL;DR: The application of a combination of convolutional neural networks for the recognition of handwritten digits is considered and the minimal handwriting recognition error was estimated.

18 citations

Proceedings ArticleDOI
25 Mar 2020
TL;DR: The main feature of the proposed solution is dealt with the fact that the proposed cascaded combination of neural networks provides a sufficiently high accuracy with a simple architecture.
Abstract: The use of a combination of a convolutional neural network and multilayer perceptrons for recognizing handwritten digits is considered. Recognition is carried out by two sets of networks following each other. The first neural network selects two digits with maximum activation functions. Depending on the winners, the following network is activated (multilayer perceptron), which selects one digit from two. The proposed algorithm is tested on the data from MNIST. The recognition error is 0.75%. Obtained results demonstrate that the minimum error with this approach is 0.68%, and the accuracy of the F-metric is about 0.99 for each digit. The main feature of the proposed solution is dealt with the fact that the proposed cascaded combination of neural networks provides a sufficiently high accuracy with a simple architecture.

8 citations

Proceedings ArticleDOI
01 Sep 2020
TL;DR: The classical six-layer neural network used to recognize handwritten digit patterns from the MNIST database is considered, and a more accurate formula is obtained for the limits, in which the initial values of the weights of the neural network are generated.
Abstract: The classical six-layer neural network is considered. This network is used to recognize handwritten digit patterns from the MNIST database. The influence of the size of mini-batches on the learning speed and pattern recognition accuracy is analyzed. The optimal sizes of mini-batch are obtained. The relationship between the accuracy of training and the accuracy of test samples is considered. The change in the values of the radius vector of the scales during training is shown. Conclusions are drawn about the influence of the initial value of the balance on the recognition accuracy. A more accurate formula is obtained for the limits, in which the initial values of the weights of the neural network are generated.

3 citations

Journal ArticleDOI
TL;DR: An algorithm for eliminating a defect is proposed, which includes a change in intensity on a mammogram and deteriorations in the contrast of individual areas and conclusions are drawn about the minimum changes in features between the original image and the image obtained by the proposed algorithm.
Abstract: Today, the processing and analysis of mammograms is quite an important field of medical image processing. Small defects in images can lead to false conclusions. This is especially true when the distortion occurs due to minor malfunctions in the equipment. In the present work, an algorithm for eliminating a defect is proposed, which includes a change in intensity on a mammogram and deteriorations in the contrast of individual areas. The algorithm consists of three stages. The first is the defect identification stage. The second involves improvement and equalization of the contrasts of different parts of the image outside the defect. The third involves restoration of the defect area via a combination of interpolation and an artificial neural network. The mammogram obtained as a result of applying the algorithm shows significantly better image quality and does not contain distortions caused by changes in brightness of the pixels. The resulting images are evaluated using Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE) and Naturalness Image Quality Evaluator (NIQE) metrics. In total, 98 radiomics features are extracted from the original and obtained images, and conclusions are drawn about the minimum changes in features between the original image and the image obtained by the proposed algorithm.

1 citations

Proceedings ArticleDOI
24 Mar 2021
TL;DR: In this paper, a discrete two-dimensional Fourier transform is applied to the original images and the real and imaginary parts are separated from the obtained complex values, as well as the amplitude and phase are calculated.
Abstract: Recognition of handwritten digits by convolutional neural network (CNN) using Fourier transforms of images as a preprocessing is considered. An algorithm of image preprocessing for effective CNN training and handwritten digits recognition is proposed. A discrete two-dimensional Fourier transform is applied to the original images. The real and imaginary parts are separated from the obtained complex values, as well as the amplitude and phase are calculated. Convolutional neural network is trained on the resulting characteristics obtained after Fourier transform. The proposed approach is tested on the MNIST database. The effects of image preprocessing using spectral decomposition and application of obtained different essential characteristics on the errors of handwritten digits recognition are estimated.

1 citations


Cited by
More filters
Journal ArticleDOI
13 Mar 2021-Entropy
TL;DR: In this paper, the authors proposed a novel context-aware model based on deep neural networks to address the challenges of recognizing offline handwritten Arabic text, including isolated digits, characters, and words.
Abstract: Offline Arabic Handwriting Recognition (OAHR) has recently become instrumental in the areas of pattern recognition and image processing due to its application in several fields, such as office automation and document processing. However, OAHR continues to face several challenges, including high variability of the Arabic script and its intrinsic characteristics such as cursiveness, ligatures, and diacritics, the unlimited variation in human handwriting, and the lack of large public databases. In this paper, we introduce a novel context-aware model based on deep neural networks to address the challenges of recognizing offline handwritten Arabic text, including isolated digits, characters, and words. Specifically, we propose a supervised Convolutional Neural Network (CNN) model that contextually extracts optimal features and employs batch normalization and dropout regularization parameters. This aims to prevent overfitting and further enhance generalization performance when compared to conventional deep learning models. We employ a number of deep stacked-convolutional layers to design the proposed Deep CNN (DCNN) architecture. The model is extensively evaluated and shown to demonstrate excellent classification accuracy when compared to conventional OAHR approaches on a diverse set of six benchmark databases, including MADBase (Digits), CMATERDB (Digits), HACDB (Characters), SUST-ALT (Digits), SUST-ALT (Characters), and SUST-ALT (Names). A further experimental study is conducted on the benchmark Arabic databases by exploiting transfer learning (TL)-based feature extraction which demonstrates the superiority of our proposed model in relation to state-of-the-art VGGNet-19 and MobileNet pre-trained models. Finally, experiments are conducted to assess comparative generalization capabilities of the models using another language database , specifically the benchmark MNIST English isolated Digits database, which further confirm the superiority of our proposed DCNN model.

28 citations

Journal ArticleDOI
TL;DR: In this paper, a hybrid model consisting of Kernel Principal Component Component Analysis (kPCA) and DNNs is proposed to detect and diagnose faults in various processes, which can serve as an important tool to detect the fault and take early corrective actions, thus enhancing process safety.

10 citations

Journal ArticleDOI
TL;DR: In this article , a hybrid model consisting of Kernel Principal Component Component Analysis (kPCA) and DNNs is proposed to detect and diagnose faults in various processes, where complex data is processed by kPCA to reduce its dimensionality, and simplified data is used for two separate DNN for training (detection and diagnosis).

10 citations

Proceedings ArticleDOI
25 Mar 2020
TL;DR: The main feature of the proposed solution is dealt with the fact that the proposed cascaded combination of neural networks provides a sufficiently high accuracy with a simple architecture.
Abstract: The use of a combination of a convolutional neural network and multilayer perceptrons for recognizing handwritten digits is considered. Recognition is carried out by two sets of networks following each other. The first neural network selects two digits with maximum activation functions. Depending on the winners, the following network is activated (multilayer perceptron), which selects one digit from two. The proposed algorithm is tested on the data from MNIST. The recognition error is 0.75%. Obtained results demonstrate that the minimum error with this approach is 0.68%, and the accuracy of the F-metric is about 0.99 for each digit. The main feature of the proposed solution is dealt with the fact that the proposed cascaded combination of neural networks provides a sufficiently high accuracy with a simple architecture.

8 citations

Proceedings ArticleDOI
01 Sep 2020
TL;DR: The classical six-layer neural network used to recognize handwritten digit patterns from the MNIST database is considered, and a more accurate formula is obtained for the limits, in which the initial values of the weights of the neural network are generated.
Abstract: The classical six-layer neural network is considered. This network is used to recognize handwritten digit patterns from the MNIST database. The influence of the size of mini-batches on the learning speed and pattern recognition accuracy is analyzed. The optimal sizes of mini-batch are obtained. The relationship between the accuracy of training and the accuracy of test samples is considered. The change in the values of the radius vector of the scales during training is shown. Conclusions are drawn about the influence of the initial value of the balance on the recognition accuracy. A more accurate formula is obtained for the limits, in which the initial values of the weights of the neural network are generated.

3 citations