Olga Shemagina

Olga Shemagina


Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
16 December 2025 in Technologies
Verified
Journal Article
Open access
PDF file
AKAndrey V. Kovalchuk
Andrey V. Kovalchuk
ALAndrey Lebedev
Andrey Lebedev
OSOlga Shemagina
Olga Shemagina
INIrina Vladimirovna Nuidel
Irina Vladimirovna Nuidel
VYVladimir Yakhno
Vladimir Yakhno
SSSergey Stasenko
Sergey Stasenko
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.

1 January 2014 in Optical Memory and Neural Networks
Verified
Journal Article
Closed access
PDF file
NBN. S. Belliustin
N. S. Belliustin
YKYu. D. Kalafati
Yu. D. Kalafati
ATAlexander Telnykh
Alexander Telnykh
OSOlga Shemagina
Olga Shemagina
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.

16 December 2022 in arXiv
Verified
Preprint
Open access
PDF file
SSSergey Stasenko
Sergey Stasenko
OSOlga Shemagina
Olga Shemagina
EEEremin Evgeny
Eremin Evgeny
VYVladimir Yakhno
Vladimir Yakhno
SPSergey Parin
Sergey Parin
SPSofia A. Polevaya
Sofia A. Polevaya
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.