Olga V. Shemagina
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Olga V. Shemagina has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Sergey V. Stasenko
Institute of Biology and Biomedicine, Lobachevsky State University of Nizhniy Novgorod, Russia
2 shared publications - Vladimir Yakhno
Federal Research Center Institute of Applied Physics Russian Academy of Sciences (IAP RAS) 46 Ulyanov Street 603950 Nizhny Novgorod Russia
2 shared publications - Alexander Telnykh
Institute of Applied Physics of the Russian Academy of Sciences, 603155 Nizhny Novgorod, Russia
1 shared publication - Andrey A. Lebedev
Neurotechnology Department, Institute of Biology and Biomedicine, Lobachevsky State University of Nizhny Novgorod, Gagarin Avenue 23, 603022 Nizhny Novgorod, Russia
1 shared publication - Andrey V. Kovalchuk
Research Center in Artificial Intelligence, Institute of Information Technologies, Mathematics and Mechanics, Lobachevsky State University of Nizhny Novgorod, 603022 Nizhny Novgorod, Russia
1 shared publication - Eremin Evgeny
Faculty of Social Sciences, Lobachevsky State University of Nizhny Novgorod, 603022 Nizhny Novgorod, Russia
1 shared publication
Latest Publications
- Open Access
- 16 December 2025
- Published by MDPI AG in Technologies
- Vol. 13 (12) , 593
Enhancing Cascade Object Detection Accuracy Using Correctors Based on High-Dimensional Feature Separation
This study addresses the problem of correcting systematic errors in classical cascade object detectors under severe data scarcity and distribution shift. We focus on the widely used Viola–Jones framework enhanced with a modified Census transform and propose a modular “corrector” architecture that can be attached to an existing detector without retraining it. The key idea is to exploit the blessing of dimensionality: high-dimensional feature vectors constructed from multiple cascade stages are transformed by PCA and whitening into a space where simple linear Fisher discriminants can reliably separate rare error patterns from normal operation using only a few labeled examples. This study presents a novel algorithm designed to correct the outputs of object detectors constructed using the Viola–Jones framework enhanced with a modified census transform. The proposed method introduces several improvements addressing error correction and robustness in data-limited conditions. The approach involves image partitioning through a sliding window of fixed aspect ratio and a modified census transform in which pixel intensity is compared to the mean value within a rectangular neighborhood. Training samples for false negative and false positive correctors are selected using dual Intersection-over-Union (IoU) thresholds and probabilistic sampling of true positive and true negative fragments. Corrector models are trained based on the principles of high-dimensional separability within the paradigm of one- and few-shot learning, utilizing features derived from cascade stages of the detector. Decision boundaries are optimized using Fisher’s rule, with adaptive thresholding to guarantee zero false acceptance. Experimental results indicate that the proposed correction scheme enhances object detection accuracy by effectively compensating for classifier errors, particularly under conditions of scarce training data. On two railway image datasets with only about one thousand images each, the proposed correctors increase Precision from 0.36 to 0.65 on identifier detection while maintaining high Recall (0.98 → 0.94), and improve digit detection Recall from 0.94 to 0.98 with negligible loss in Precision (0.92 → 0.91). These results demonstrate that even under scarce training data, high-dimensional feature separation enables effective one-/few-shot error correction for cascade detectors with minimal computational overhead.
- 16 December 2025
- Published by MDPI AG in Technologies
- Vol. 13 (12) , 593
Open AccessEnhancing Cascade Object Detection Accuracy Using Correctors Based on High-Dimensional Feature Separation
This study addresses the problem of correcting systematic errors in classical cascade object detectors under severe data scarcity and distribution shift. We focus on the widely used Viola–Jones framework enhanced with a modified Census transform and propose a modular “corrector” architecture that can be attached to an existing detector without retraining it. The key idea is to exploit the blessing of dimensionality: high-dimensional feature vectors constructed from multiple cascade stages are transformed by PCA and whitening into a space where simple linear Fisher discriminants can reliably separate rare error patterns from normal operation using only a few labeled examples. This study presents a novel algorithm designed to correct the outputs of object detectors constructed using the Viola–Jones framework enhanced with a modified census transform. The proposed method introduces several improvements addressing error correction and robustness in data-limited conditions. The approach involves image partitioning through a sliding window of fixed aspect ratio and a modified census transform in which pixel intensity is compared to the mean value within a rectangular neighborhood. Training samples for false negative and false positive correctors are selected using dual Intersection-over-Union (IoU) thresholds and probabilistic sampling of true positive and true negative fragments. Corrector models are trained based on the principles of high-dimensional separability within the paradigm of one- and few-shot learning, utilizing features derived from cascade stages of the detector. Decision boundaries are optimized using Fisher’s rule, with adaptive thresholding to guarantee zero false acceptance. Experimental results indicate that the proposed correction scheme enhances object detection accuracy by effectively compensating for classifier errors, particularly under conditions of scarce training data. On two railway image datasets with only about one thousand images each, the proposed correctors increase Precision from 0.36 to 0.65 on identifier detection while maintaining high Recall (0.98 → 0.94), and improve digit detection Recall from 0.94 to 0.98 with negligible loss in Precision (0.92 → 0.91). These results demonstrate that even under scarce training data, high-dimensional feature separation enables effective one-/few-shot error correction for cascade detectors with minimal computational overhead.
- Open Access
Using machine learning algorithms to determine the emotional disadaptation of a person by his rhythmogram
In this study we applyed machine-learning algorithms to determine the emotional disadaptation of a person by his rhythmogram. We used the method of determining a subject level of emotional disadaptation and recording of cardiorhythmography. We show that electrocardiogram (ECG) signals can be used for the registration of the emotional disadaptation of a person.
Open AccessUsing machine learning algorithms to determine the emotional disadaptation of a person by his rhythmogram
In this study we applyed machine-learning algorithms to determine the emotional disadaptation of a person by his rhythmogram. We used the method of determining a subject level of emotional disadaptation and recording of cardiorhythmography. We show that electrocardiogram (ECG) signals can be used for the registration of the emotional disadaptation of a person.
- 1 January 2014
- Published by Allerton Press in Optical Memory and Neural Networks
- Vol. 23 (1) , 26-33
Neuron-like algorithms of adaptive segmentation and semantic description of images in the “adult image” recognition problem
We describe the possibility of using the methods of color segmentation and semantic description of images in the “adult image” recognition problem. A method for the construction of an adaptive color model of human skin, which uses information about the faces found in the image, is proposed. The possibility of using the semantic features obtained by face attribute detectors for a more detailed classification of such images is also considered.
- 1 January 2014
- Published by Allerton Press in Optical Memory and Neural Networks
- Vol. 23 (1) , 26-33
Neuron-like algorithms of adaptive segmentation and semantic description of images in the “adult image” recognition problem
We describe the possibility of using the methods of color segmentation and semantic description of images in the “adult image” recognition problem. A method for the construction of an adaptive color model of human skin, which uses information about the faces found in the image, is proposed. The possibility of using the semantic features obtained by face attribute detectors for a more detailed classification of such images is also considered.