scholarly journals DEVELOPMENT OF MACHINE LEARNING METHOD WITH BIOMETRIC PROTECTION WITH NEW FILTRATION METHODS

2021 ◽  
Vol 3 (11) ◽  
pp. 16-30
Author(s):  
Mariya Nazarkevych ◽  
Yaroslav Voznyi ◽  
Hanna Nazarkevych
Keyword(s):  
Machine Learning ◽  
Wavelet Transforms ◽  
Gabor Filter ◽  
Signal To Noise Ratio ◽  
Gabor Wavelet ◽  
Gabor Filtering ◽  
Flexible Control ◽  
Gabor Function ◽  
Machine Learning Methods ◽  
Good Filtration

Biometric images were processed and filtered by a newly developed Ateb-Gabor wavelet filter. Identification of biometric images was performed by machine learning methods. The Gabor filter based on Ateb functions is effective for filtering because it contains generalizations of trigonometric functions. Developed wavelet transform of Ateb-Gabor function. It is shown that the function depends on seven parameters, each of which makes significant changes in the results of filtering biometric images. A study of the wavelet Ateb-Gabor function was performed. The graphical dependences of the Gabor filter wavelet and the Ateb-Gabor filter wavelet are constructed. The introduction of wavelet transforms reduces the complexity of Ateb-Gabor filter calculations by simplifying function calculations and reducing filtering time. The complexity of the algorithms for calculating the Gabor filter wavelet and the Ateb-Gabor filter wavelet is evaluated. Ateb-Gabor filtering allows you to change the intensity of the entire image, and to change certain ranges, and thus change certain areas of the image. It is this property that biometric images should have, in which the minions should be contrasting and clear. Ateb functions have the ability to change two rational parameters, which, in turn, will allow more flexible control of filtering. The properties of the Ateb function are investigated, as well as the possibility of changing the amplitude of the function, the oscillation frequency to the numerical values ​​of the Ateb-Gabor filter. By using the parameters of the Ateb function, you can get a much wider range of shapes and sizes, which expands the number of possible filtering options. You can also implement once filtering, taking into account the direction of the minutes and reliably determine the sharpness of the edges, rather than filtering batocrates. The reliability results were tested on the basis of NIST Special Database 302, and good filtration results were shown. This was confirmed by a comparison experiment between the Wavelet-Gabor filtering and the Ateb-Gabor wavelet function based on the measurement of the PSNR signal-to-noise ratio.

scholarly journals WAVELET TRANSFORMATION ATEB-GABOR FILTERS TO BIOMETRIC IMAGES

2020 ◽  
Vol 3 (7) ◽  
pp. 115-130
Author(s):  
Mariya Nazarkevych ◽  
Yaroslav Voznyi ◽  
Sergiy Dmytryk
Keyword(s):  
Wavelet Transform ◽  
Wavelet Transformation ◽  
Gabor Filter ◽  
Signal To Noise Ratio ◽  
Gabor Wavelet ◽  
Reliability Of Results ◽  
Ratio Measurement ◽  
Flexible Control ◽  
Gabor Function ◽  
Good Filtration

Biometric images were pre-processed and filtered in two ways, by wavelet- Gabor and wavelet Ateb-gabor filtration. Ateb-based Gabor filter is effective for filtration because it contains generalizations of trigonometric functions. The wavelet transform of Ateb-Gabor function was developed. The function dependence on seven parameters was shown, each of them significantly changes the filtering results of biometric images. The Ateb-Gabor wavelet research was performed. Graphic dependencies of the wavelet Gabor filter and the wavelet Ateb-Gabor filter were constructed. The appliance of wavelet transform makes it possible to reduce the complexity of calculating an Ateb-Gabor filter by simplifying function calculations and reducing filtering time. The complexities of algorithms for calculating the wavelet Gabor filter and the wavelet Ateb-Gabor filter have been evaluated. Ateb-Gabor filtration allows you to adjust the intensity of the entire image, and to change certain ranges, thereby changing certain areas of the image. Biometric images should have this property, on which the minucius should be contrasting and clear. Ateb functions have the property of changing two rational parameters, which will allow to make more flexible control of filtration. The properties of the Ateb function, as well as the possibility of changing the amplitude of the function, the oscillation frequency by the numerical values of the Ateb-Gabor filter, were investigated. By using the parameters of the Ateb function, you can get a much larger range of shapes and sizes, which expands the number of possible filtration options. You can also perform filtration once, taking into account the direction of the minucius and reliably determine the sharpness of the edges, rather than perform filtration many times. The reliability of results were tested using NIST Special Database 302 and good filtration results were shown. This is confirmed by the comparison experiment between the wavelet-Gabor filter and the wavelet Ateb-Gabor function based on the PSNR signal-to-noise ratio measurement.

scholarly journals Applying Ateb–Gabor Filters to Biometric Imaging Problems

Symmetry ◽  
2021 ◽  
Vol 13 (4) ◽  
pp. 717
Author(s):  
Mariia Nazarkevych ◽  
Natalia Kryvinska ◽  
Yaroslav Voznyi
Keyword(s):  
Wavelet Transformation ◽  
Symmetric Functions ◽  
Gabor Filter ◽  
Signal To Noise Ratio ◽  
The Other ◽  
Mean Square ◽  
Image Transformation ◽  
Gabor Filtering ◽  
Signal To Noise ◽  
Filtration Method

This article presents a new method of image filtering based on a new kind of image processing transformation, particularly the wavelet-Ateb–Gabor transformation, that is a wider basis for Gabor functions. Ateb functions are symmetric functions. The developed type of filtering makes it possible to perform image transformation and to obtain better biometric image recognition results than traditional filters allow. These results are possible due to the construction of various forms and sizes of the curves of the developed functions. Further, the wavelet transformation of Gabor filtering is investigated, and the time spent by the system on the operation is substantiated. The filtration is based on the images taken from NIST Special Database 302, that is publicly available. The reliability of the proposed method of wavelet-Ateb–Gabor filtering is proved by calculating and comparing the values of peak signal-to-noise ratio (PSNR) and mean square error (MSE) between two biometric images, one of which is filtered by the developed filtration method, and the other by the Gabor filter. The time characteristics of this filtering process are studied as well.

scholarly journals Quantized Constant-Q Gabor Atoms for Sparse Binary Representations of Cyber-Physical Signatures

Entropy ◽  
2020 ◽  
Vol 22 (9) ◽  
pp. 936
Author(s):  
Milton A. Garcés
Keyword(s):  
Machine Learning ◽  
Wavelet Transforms ◽  
Signal To Noise Ratio ◽  
Continuous Wavelet ◽  
Signal To Noise ◽  
Weighting Functions ◽  
Signal Characteristics ◽  
Multiple Sensor ◽  
New Challenges ◽  
Physical Signal

Increased data acquisition by uncalibrated, heterogeneous digital sensor systems such as smartphones present new challenges. Binary metrics are proposed for the quantification of cyber-physical signal characteristics and features, and a standardized constant-Q variation of the Gabor atom is developed for use with wavelet transforms. Two different continuous wavelet transform (CWT) reconstruction formulas are presented and tested under different signal to noise ratio (SNR) conditions. A sparse superposition of Nth order Gabor atoms worked well against a synthetic blast transient using the wavelet entropy and an entropy-like parametrization of the SNR as the CWT coefficient-weighting functions. The proposed methods should be well suited for sparse feature extraction and dictionary-based machine learning across multiple sensor modalities.

Face Recognition Based on Gabor Filter and Improved Linear Local Tangent Space Alignment Algorithm

2014 ◽  
Vol 989-994 ◽  
pp. 4091-4094
Author(s):  
Xue Yan Xu ◽  
Jiao Yu Liu ◽  
Yuan Shi ◽  
Tuo Deng
Keyword(s):  
Face Recognition ◽  
Tangent Space ◽  
Gabor Filter ◽  
Recognition Rate ◽  
Gabor Wavelet ◽  
Alignment Algorithm ◽  
Gabor Filtering ◽  
The Face ◽  
Secondary Feature ◽  
Local Tangent

In this paper, Gabor filtering and linear local tangent space alignment algorithm and its improved algorithm are used on face recognition. The Gabor wavelet transform can detect the image information in different directions and scales, according to its selective direction and frequency characteristics. The LLTSA reduces the dimension of the sample while the LLTSA and the other improved algorithms extract secondary feature. Experiment and analyze the average recognition rate of the LLTSA and its improved algorithms with the variation of dimension. The experiment results show the effectiveness of the method, increasing the face recognition accuracy.

scholarly journals Automated and unbiased classification of motor neuron phenotypes with single cell resolution in ALS tissue

2020 ◽  
Author(s):  
Cathleen Hagemann ◽  
Giulia E. Tyzack ◽  
Doaa M. Taha ◽  
Helen Devine ◽  
Linda Greensmith ◽  
...  
Keyword(s):  
Machine Learning ◽  
Image Processing ◽  
Single Cell ◽  
Motor Neurons ◽  
Signal To Noise Ratio ◽  
Histopathological Analysis ◽  
Learning Methods ◽  
Tissue Samples ◽  
Tissue Sections ◽  
Machine Learning Methods

SUMMARYHistopathological analysis of tissue sections is an invaluable resource in neurodegeneration research. Importantly, cell-to-cell variation in both the presence and severity of a given phenotype is however a key limitation of this approach, reducing the signal to noise ratio and leaving unresolved the potential of single-cell scoring for a given disease attribute. Here, we developed an image processing pipeline for automated identification and profiling of motor neurons (MNs) in amyotrophic lateral sclerosis (ALS) pathological tissue sections. This approach enabled unbiased analysis of hundreds of cells, from which hundreds of features were readily extracted. Next by testing different machine learning methods, we automated the identification of phenotypically distinct MN subpopulations in VCP- and SOD1-mutant transgenic mice, revealing common aberrant phenotypes in cellular shape. Additionally we established scoring metrics to rank cells and tissue samples for both disease probability and severity. Finally, by adapting this methodology to human post-mortem tissue analysis, we validated our core finding that morphological descriptors strongly discriminate ALS from control healthy tissue at the single cell level. In summary, we show that combining automated image processing with machine learning methods substantially improves the speed and reliability of identifying phenotypically diverse MN populations. Determining disease presence, severity and unbiased phenotypes at single cell resolution might prove transformational in our understanding of ALS and neurodegenerative diseases more broadly.

Sign in / Sign up

Export Citation Format

Share Document