=Paper= {{Paper |id=Vol-3646/Paper_4.pdf |storemode=property |title=Exploring Conditions of Image Samples Formation for Person Identification Information Technology |pdfUrl=https://ceur-ws.org/Vol-3646/Paper_4.pdf |volume=Vol-3646 |authors=Oleksii Bychkov,Kateryna Merkulova,Yelyzaveta Zhabska |dblpUrl=https://dblp.org/rec/conf/iti2/BychkovMZ23 }} ==Exploring Conditions of Image Samples Formation for Person Identification Information Technology== https://ceur-ws.org/Vol-3646/Paper_4.pdf

Exploring Conditions of Image Samples Formation for Person
Identification Information Technology
Oleksii Bychkov, Kateryna Merkulova and Yelyzaveta Zhabska
Taras Shevchenko National University of Kyiv, Volodymyrska str. 64/13, Kyiv, 01601, Ukraine

Abstract
This paper describes the research the algorithm underlying in the basis of information
technology of face recognition and person identification with an aim to improve its
performance by exploring the conditions of forming image samples and effect caused by
properties of the images containing in the samples on the algorithm efficiency.
Researched algorithm is based on Haar features as method of localizing of face area on the
image, Gabor wavelets as method of face image processing, 1-dimensional local binary
patterns and histogram of oriented gradients as methods of face image feature extraction.
During the experimental research several sets of experiments were conducted on face images
from several different databases that contain images captured under constrained and
unconstrained environmental conditions. After first set of experiments, that were conducted on
image samples formed by extracting images with unrecognizable face areas and expanding the
etalon samples of images captured under unconstrained conditions, the performance of the
algorithm was improved on 7.5-45%. Although the influence of image format and resolution
on algorithm performance was explored. As a result of experiments, it was established that
format conversion might have an impact on identification accuracy rate by increasing it on 5%
after converting images to JPG format. Resolution conversion improved algorithm
performance on 5-20% on initial image samples from databases of images captured in
constrained and unconstrained conditions and 5-35% on expanded image samples from
databases of images captured in unconstrained conditions.
After all, it was found that reforming of etalon image samples by expanding it and resolution
conversion of the images have the biggest impact on the algorithm performance. As a result,
the highest identification accuracy of 95% on the images from the SCface and FERET
databases was obtained.

Keywords 1
Information technology, face recognition, biometric identification.

1. Introduction
Face recognition technologies have emerged as a powerful tool for identifying individuals by
analyzing their facial features. Over the recent years, face recognition has garnered substantial attention
owing to its utility across diverse domains, encompassing applications such as security and surveillance,
biometric authentication, human-computer interaction, healthcare, and other pertinent security-related
fields [1]. As with most biometric applications, changes in appearance caused by an unconstrained
environment tend to cause problems with face recognition. Let's consider some problems that need to
be solved in the near future [1, 2]:
1. Occlusion. A face can be photographed in an arbitrary pose in a certain environment and without
any user input, so it is possible that the image will only contain a partial face.
2. Aging of the face. As the age gap between the query image and the reference image of the same
person increases, the accuracy of recognition systems usually decreases.

Information Technology and Implementation (IT&I-2023), November 20-21, 2023, Kyiv, Ukraine
EMAIL: bos.knu@gmail.com (O. Bychkov); kate.don11@gmail.com (K. Merkulova); y.zhabska@gmail.com (Y. Zhabska)
ORCID: 0000-0002-9378-9535 (O. Bychkov); 0000-0001-6347-5191 (K. Merkulova); 0000-0002-9917-3723 (Y. Zhabska)
©️ 2023 Copyright for this paper by its authors.
Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
CEUR Workshop Proceedings (CEUR-WS.org)

CEUR
ceur-ws.org
Workshop ISSN 1613-0073
Proceedings
33
3. A single sample. In real-world applications (e.g., passports, immigration systems), only one model
of each person is registered in the database and available for the recognition task.
4. Video surveillance. Camera focus issues that can lead to image blur, low-resolution or
compression errors, and blocky effects.
Face recognition technologies have become widely used in many applications [3]. Some of the most
common areas of application nowadays are criminal investigations and identification of missing
individuals. Moreover, face recognition technology can already be deployed on drones as part of special
operations missions to help operators with intelligence gathering, reconnaissance, and identifying
targets [4]. The fact of these means that face recognition technologies are increasingly being used in
sensitive areas, as military operation, where any mistake can be crucial. Therefore, it is important to
explore in detail information technologies of face recognition and identification to reduce the possibility
of failure occurrence before they will be widely used in any purposes.

2. Task definition and solution methods
In our previous studies [5] there was introduced and explored a novel information technology for
face recognition and identification based on local-texture descriptors. This technology relies on an
algorithm that incorporates several methods such as Haar features, Gabor wavelet transform, local
binary patterns in a 1-dimensional space and histogram of oriented gradients. These methods are
employed for tasks of face localizing, image processing, extraction of feature vectors, respectively.
More elaborate explanation of the algorithm's workings is provided as follows.
The algorithm takes a portrait image of a person as its input. This image is then transformed into
grayscale and scanned to localize the face region. This localized face region is subsequently singled out
for more targeted processing. To localize the face region the Haar features are used [6]. These features
encompass a collection of elemental patterns, comprising both white and black blocks. Upon training
the image features fj, it becomes feasible to derive the threshold value θj and the modulated
comparability value modulo pj. The basic classifier can be described as:
1, 𝑖𝑓 𝑝𝑗 𝑓𝑗 (𝑥) < 𝑝𝑗 𝜃𝑗 ,
ℎ𝑗 (𝑥) = { (1)
0, 𝑒𝑙𝑠𝑒.
The outcome of applying the classifier to identify faces within an image comprises a collection of
rectangles. These rectangles essentially represent a series of coordinates, denoting the corners of the
region where a human face is positioned within the image. Following this detection, the original image
matrix undergoes a reduction, retaining only the elements corresponding to the area where the human
face is positioned.
Once the face region of the image is recognized, it undergoes processing through the Gabor wavelet
transform [7]. This transformation is applied multiple times to the facial area image, varying certain
parameters of the wavelet function. The objective is to aggregate all the outcomes to generate a
comprehensive global facial representation of the person.
Within the Gabor representation [8], the arbitrary function F(x) is expanded by considering both
symmetric and asymmetric elementary signals.
(𝑥 − 𝑥𝑚 )2
𝑆𝑠 (𝑥) = 𝑒𝑥𝑝 [− ] 𝑐𝑜𝑠[2𝜋𝑓𝑛 (𝑥 − 𝑥𝑚 )] (2)
4𝜎 2
(𝑥 − 𝑥𝑚 )2
𝑆𝑎 (𝑥) = 𝑒𝑥𝑝 [− ] 𝑠𝑖𝑛[2𝜋𝑓𝑛 (𝑥 − 𝑥𝑚 )] (3)
4𝜎 2
These signals are centered at the position x = xm and at the spatial frequency f = fn with a Gaussian
envelope described by the standard deviation 𝜎.
The complex Gabor function in the spatial domain can be denoted as follows:
𝑔(𝑥, 𝑦) = 𝑠(𝑥, 𝑦)𝜔𝜏 (𝑥, 𝑦), (4)
where s(x, y) is a complex sinusoid known as the carried and ωτ(x, y) is a 2D Gaussian function known
as the envelope function.
Complex sinusoid can be described with the following:
𝑠(𝑥, 𝑦) = exp(𝑗(2𝜋𝐹0 (𝑥 cos 𝜔0 + 𝑦 sin 𝜔0 ) + 𝑃)). (5)

34
where parameters x · cos ω0 and y · cos ω0 define spatial frequency of the sinusoid in polar coordinates,
F0 is magnitude and ω0 defines direction.
Gaussian function can be defined as:
𝜔𝜏 (𝑥, 𝑦) = 𝐾 𝑒𝑥𝑝(−𝜋(𝑎2 (𝑥 − 𝑥0 )2𝜏 + 𝑏 2 (𝑦 − 𝑦0 )2𝜏 )), (6)
where (x0, y0) is the peak of the function, a and b are the Gaussian scaling parameters, and the subscript
τ denotes the rotation operation as follows:
(𝑥 − 𝑥0 )𝜏 = (𝑥 − 𝑥0 ) cos 𝜃 + (𝑦 − 𝑦0 ) sin 𝜃, (7)
(𝑦 − 𝑦0 )𝜏 = −(𝑥 − 𝑥0 ) sin 𝜃 + (𝑦 − 𝑦0 ) cos 𝜃. (8)
A family of two-dimensional Gabor wavelets that satisfies wavelet theory and neurophysiological
constraints for simple cells can be obtained using the following formulas:
𝜔0 𝜔02
− (4(𝑥 cos 𝜃+𝑦 sin 𝜃)2 +(−𝑥 sin 𝜃+𝑦 cos 𝜃)2 )
𝜓(𝑥, 𝑦, 𝜔0 , 𝜃) = 𝑒 8𝜅 2
√2𝜋𝜅 (9)
𝜅2
𝑖(𝜔0 𝑥 cos 𝜃+𝜔0 𝑦 sin 𝜃) −
∙ [𝑒 −𝑒 2 ],

where ω0 is the radial frequency in radians per unit length and T is the orientation of the wavelet in
radians. The Gabor wavelet is centered at the position (x = 0, y = 0), and the normalization coefficient
is such that <ψ, ψ> = 1, i.e. normalized by L2. κ is a constant, with κ ≈ π for a one-octave frequency
range and κ ≈ 2.5 for a 1.5-octave frequency range.
The technique of employing local binary patterns in a 1-dimensional space [9] is harnessed to derive
a feature vector from the comprehensive face image acquired following the Gabor wavelet
transformation. This approach has demonstrated robust and efficient performance outcomes even when
dealing with variations in angles of rotation and lighting conditions. It involves generating a 1-
dimensional row projection for each image matrix level, which serves as a descriptor for capturing and
examining the texture within the facial image. The computation of the local binary patterns descriptor
can be achieved using the following formula:
1DLBP = ∑n=0N-1S(gn – g0) · 2n, (10)
where g0 is a value of the central element, gn is the value of 1-dimensional neighboring element and S(x)
is defined with the following:
1 𝑖𝑓 𝑥 ≥ 0;
𝑆(𝑥) = { (11)
0 𝑜𝑡ℎ𝑒𝑟𝑤𝑖𝑠𝑒.
Based on preceding research, it was deduced that employing a single method for feature vector
extraction is less effective when compared to their combination. Consequently, the decision was made
to enhance the feature vector obtained from 1-dimensional local binary patterns with another vector
derived through the creation of a histogram of oriented gradients [10]. The essence of this technique
lies in preserving information regarding image shape characteristics within histograms that pertain to
object boundaries found within sub-ranges of images post wavelet transformation. The count of object
boundary orientations falling within specific ranges is depicted by each interval in the histogram. In the
context of a grayscale image, derivatives are computed along both the x and y axes for every pixel. The
magnitude of the gradient can be expressed as follows:
|𝐺| = √𝐼 2 (𝑥) + 𝐼 2 (𝑦). (12)
The orientation calculation can be described as follows:
𝐼𝑦
𝜃 = 𝑎𝑐𝑟𝑡𝑎𝑛 . (13)
𝐼𝑥
To form the comprehensive feature vector, both the resulting vectors from the 1-dimensional local
binary patterns and the histogram of oriented gradients are combined. This resultant global feature
vector can then be employed for subsequent person classification and identification based on the input
image containing their face. The purpose of this research is to explore the conditions of image sample
formation, to which the algorithm is applied, to investigate the algorithm performance in condition of

35
its appliance to images captured in constrained and unconstrained conditions, as well as the ways of
improving the resulting identification accuracy rates.

3. Experimental research
With an aim to explore and improve performance of the information technology for face recognition
and person identification by face image, based on Haar features, Gabor wavelet transform, histograms
of oriented gradients (HOG) and local binary patterns in one-dimensional space (1DLBP), it was
decided to conduct the experiments on different databases, that contain images captured under different
conditions of fixation regarding the intensity of lighting, the presence of cosmetics, makeup or occlusive
elements, subjects’ age variability, head postures and facial expressions variability, etc. For
experimental research several databases were chosen such as Database of Faces (DoF, formerly “The
ORL Database of Faces”) [11], FERET (Face Recognition Technology database) [12], SCface [13, 14],
CFP (Celebrities in Frontal-Profile data set) [15], Tinyface [16], LFW (Labeled Faces in the Wild) [17]
and AgeDB [18].
The initial set of experiments was focused on determining the efficiency of the algorithm, underlying
in the basis of information technology of face recognition and person identification by face image under
exploration, after its appliance to original face images containing in the databases. To conduct the
experiment the face images of 40 individuals were used to form the etalon and test samples. Such
number was conditioned by the minimum number of individual images of which are contained in one
of the databases, which is the Database of Faces. To perform experiments more clear, the face images
for the same number of individuals were selected from other databases as well. In Table 1 the obtained
results of these experiments are presented.
Table 1
Results of experiments on initial image samples
Total number of individuals / Accuracy / error Number of correctly / incorrectly
Database
images identification rate identified images
DoF 40 / 120 72.5% / 27.5% 29 / 11
FERET 40 / 99 75% / 25% 30 / 10
SCface 40 / 160 95% / 5% 38 / 2
CFP 40 / 120 17.5% / 82.5% 7 / 33
Tinyface 40 / 120 2.5% / 97.5% 1 / 39
LFW 40 / 120 10% / 90% 4 / 36
AgeDB 40 / 120 5% / 95% 2 / 38

During the experimental research on original face images and after analyzing its results, it was
established that on some images the algorithm is not capable to localize face region. Moreover, the
efficiency of the researched algorithm on the face images from such databases as Database of Faces,
FERET and SCface significantly exceeds the algorithm performance on the face images from CFP,
Tinyface, LFW and AgeDB databases. For the set of first three databases the identification accuracy
rate of the algorithm is greater on 70%-77.5% in comparison to other databases.
In order to explain such significant variation in algorithm performance results, it is worth to explore
in detail the databases on the image from which the experiments were conducted. Database of Faces
contains 92×112-pixeled face images of 40 people, which were captured on the dark uniform
background in a vertical frontal position of the subject under conditions of varying lighting, facial
expressions and facial details. FERET (Face Recognition Technology database) is a database that
contains 1564 sets of 256×384-pixeled images of 1199 people taken during 2 years in a semi-
constrained environment with the same physical settings for each session. SCface contains 4,160 static
images of 130 people with the size of 75×100, 108x144 and 168×224 pixels captured on the same
background, under unconstrained lighting conditions, with variation of fixed head positions. CFP
dataset contains frontal and profile images for 500 individuals from open access captured in both
constrained and unconstrained environments, with certain change of poses while other variations of
image characteristics are unrestricted. Tinyface dataset consists of face images of 5,139 individuals
with average size of 20×16 pixels captured under unconstrained conditions regarding background,

36
lighting, face positioning and the presence of occlusion. LFW contains 250×250-pixeled images of
5,749 different people captured in the environment, that is as close as possible to the natural
environment, and characterized with a wide range of variations in background, lighting, pose, facial
expression, race, ethnicity, age, etc. AgeDB contains images for 568 individuals taken with huge age
variety of the same subject in unconstrained conditions regarding poses, facial expressions, occlusion,
and noise.
Analyzing the specifics of the conditions, under which the face images from all selected databases
were captured, it can be concluded that the researched algorithm performed more efficiently during its
appliance on the images captured in semi-constrained or constrained conditions regarding the
background, lighting, subject’s head position, camera position in relate to the subject, and other physical
settings. Also, the images from the Database of Faces, FERET and SCface database are uniformed
within the single database, as far as they were not taken in conditions close to the real-world conditions.
On the other hand, CFP, Tinyface, LFW and AgeDB databases contain face images, that were captured
in unconstrained conditions and more often are not uniformed within one database, as far as they were
taken from the open access. Therefore, these databases contain images that are highly variative
regarding the background, amount and intensity of lighting, head positions, occlusive elements, age and
time intervals of capturing, makeup and cosmetics, etc.
So, considering the aforementioned problems, that significantly affect the performance of the
algorithm under research, it was decided to perform the next set of experiments with several changes
relatively to the first set of experiments. To overcome the problem of inability to localize face region
on some of the images, the etalon and test image samples was reformed by extracting those images, in
which the face region in not recognizable due to extreme angle of head rotation, excessive lighting or
other conditions, that make face features not fully visible on the image. As for the images captured
under unconstrained conditions, the etalon image sample was expanded with other images with
recognizable face features of the same individuals, which face images were already in the sample. The
results of experiments are presented in Table 2.
Table 2
Results of the experiments performed after reforming of etalon and test image samples
Total number of Accuracy / error Number of correctly / incorrectly
Database
individuals / images identification rate identified images
DoF 40 / 120 80% / 20% 32 / 8
FERET 40 / 90 95% / 5% 38 / 2
SCface 40 / 136 95% / 5% 38 / 2
40 / 120 45% / 55% 18 / 22
CFP
40 / 364 60% / 40% 24 / 16
40 / 80 10% / 90% 4 / 36
Tinyface
40 / 138 10% / 90% 4 / 36
40 / 120 55% / 45% 22 / 18
LFW
40 / 210 45% / 55% 18 / 22
40 / 120 30% / 70% 12 / 28
AgeDB
40 / 308 45% / 55% 18 / 22

Comparison diagram of described two sets of experiments is depicted in Figure 1. As can be seen,
the extraction of images, in which the face region was not recognizable, allowed to increase the
identification accuracy rate of the algorithm after its appliance on the images from the Database of
Faces on 7.5%, FERET on 20%, CFP on 27.5%, Tinyface on 7.5%, LFW on 45% and AgeDB on 25%.
Also, the expansion of etalon image samples for databases that contain images captured in
unconstrained conditions has led to the improvement of the efficiency of the algorithm on 15% for the
CFP and AgeDB databases, while result for Tinyface database remained the same and for LFW database
decreased on 10%.
Obtained results of experiments are varying in the wide range of identification accuracy rates. Such
variability may be caused by the fact that the selected databases contain images with different file format
and resolution. Therefore, it was decided to conduct the experiments in order to determine whether it
possible to improve the algorithm performance by eliminating image properties variability and by that,

37
possibly, reduce the range of algorithm performance results. Also, as was described in our previous
research [19], variety in quality of the images, which is as well determined by format and resolution,
may cause the failure of identification process if images in etalon and test image samples are not unified.
On the assumption that such properties of images as format and resolution may affect the researched
algorithm performance, it was decided to convert original images from selected databases to the most
common formats and resolutions and those on which the algorithm efficiency was the highest among
all sets of experiments and conduct the experiments by applying the algorithm on converted images.

Figure 1: Experimental results obtained on initial samples with face region extractable images in
To perform the experiments on format-converted images the following formats were selected: JPG,
PNG, and BMP. Experimental results obtained after appliance of the researched algorithm to the
samples of images with format conversion are presented in Table 3.
Table 3
Results of the experiments performed on format converted image samples
Total number of Accuracy / error Number of correctly / incorrectly
Database
individuals / images identification rate identified images
DoF JPG 40 / 120 85% / 15%
FERET PNG, BMP 40 / 120 80% / 20%
SCface JPG, PNG, BMP 40 / 90 95% / 5%
JPG, PNG, BMP 40 / 136 95% / 5%
CFP
JPG, PNG, BMP 40 / 120 45% / 55%
JPG, PNG, BMP 40 / 364 60% / 40%
Tinyface
JPG, PNG, BMP 40 / 80 10% / 90%
JPG, PNG, BMP 40 / 138 10% / 90%
LFW
JPG, PNG, BMP 40 / 120 55% / 45%
JPG 40 / 210 40% / 60%
AgeDB
PNG, BMP 40 / 210 45% / 55%

Comparative diagram of above-described set of experiments demonstrated in Figure 2. Analyzing
the results, it can be concluded that the format conversion was effective only after appliance of the
algorithm under research to the samples of images from Database of Faces – the identification accuracy
rate of the algorithm increased on 5% after converting images to JPG format. Also, variation of results
is observed in case of LFW– efficiency of the algorithm has decreased on 5% in case of expanded etalon
images sample, while the rate of identification accuracy remained the same in case of initial number of
images in the sample. The performance of the algorithm after its appliance on the images samples from
other databases have not been influenced by format conversion – identification accuracy rates for
samples of images from those databases remained stable for all experiments. Nevertheless, even such
minor changes in identification accuracy rates indicate that the format conversion in individual cases of
the algorithm appliance can be crucial for success of identification process.

38
Figure 2: Experimental results obtained on initial samples with face region extractable images in
compare to experimental results obtained on samples with format-converted images and after
expansion of etalon samples
The next set of experiments was conducted with resolution conversion. The values of resolution
were chosen with regard to those images, on which the previous experiments showed the highest rates
of identification accuracy. Since all of the selected databases contain images with different resolutions,
and simultaneous change of height and width may cause the alteration of face features depicted in the
image, which are essential for successful performance of the algorithm, it was decided to automatically
define the width value of image resolution in relation to the value of height that was set as constant.
According to this, the following values of resolution were chosen to form the image samples: width
×91, width × 100, width × 128, width × 144. Results obtained on resolution-converted images are
presented in Table 4.
Analyzing the results, presented in the diagram in Figure 3 and obtained after appliance of the
researched algorithm on the samples of resolution-converted images in compare to the results of
previously described experiments, as can be seen from the identification accuracy rates of the algorithm
changed in the following way for the samples of face images from databases.

Figure 3: Experimental results obtained on initial samples with face region extractable images in
compare to experimental results obtained on samples with resolution-converted images and after
expansion of etalon samples

39
Table 4
Results of the experiments performed on resolution converted image samples
Total number of Accuracy / error Number of correctly / incorrectly
Database
individuals / images identification rate identified images
width x 91
DoF 40 / 120 85% / 15% 34 / 6
FERET 40 / 90 65% / 35% 26 / 14
SCface 40 / 136 65% / 35% 26 / 14
40 / 120 50% / 50% 20 / 20
CFP
40 / 364 65% / 35% 26 / 14
40 / 80 25% / 75% 10 / 30
Tinyface
40 / 138 45% / 55% 18 / 22
40 / 120 40% / 60% 16 / 24
LFW
40 / 210 40% / 60% 16 / 24
40 / 120 40% / 60% 16 / 24
AgeDB
40 / 308 45% / 55% 18 / 22
width x 100
DoF 40 / 120 90% / 10% 36 / 4
FERET 40 / 90 80% / 20% 32 / 8
SCface 40 / 136 70% / 30% 28 / 12
40 / 120 60% / 40% 24 / 16
CFP
40 / 364 70% / 30% 28 / 12
40 / 80 25% / 75% 10 / 30
Tinyface
40 / 138 45% / 55% 18 / 22
40 / 120 35% / 65% 14 / 26
LFW
40 / 210 30% / 70% 12 / 28
40 / 120 40% / 60% 16 / 24
AgeDB
40 / 308 40% / 60% 16 / 24
width x 128
DoF 40 / 120 85% 15% 34 / 6
FERET 40 / 90 85% 15% 34 / 6
SCface 40 / 136 85% 15% 34 / 6
40 / 120 50% / 50% 20 / 20
CFP
40 / 364 60% / 40% 24 / 16
40 / 80 20% / 80% 8 / 32
Tinyface
40 / 138 35% / 65% 14 / 26
40 / 120 35% / 65% 14 / 26
LFW
40 / 210 70% / 30% 28 / 12
40 / 120 50% / 50% 20 / 20
AgeDB
40 / 308 45% / 55% 18 / 22
width x 144
DoF 40 / 120 85% 15% 34 / 6
FERET 40 / 90 90% / 10% 36 / 4
SCface 40 / 136 95% / 5% 38 / 2
40 / 120 40% / 60% 16 / 24
CFP
40 / 364 65% / 35% 26 / 14
40 / 80 25% / 75% 10 / 30
Tinyface
40 / 138 35% / 65% 14 / 26
40 / 120 45% / 55% 18 / 22
LFW
40 / 210 45% / 55% 18 / 22
40 / 120 40% / 60% 16 / 24
AgeDB
40 / 308 35% / 65% 14 26

40
Database of Faces – increased on 5%-10%, FERET – decreased on 5%-35%, SCface – decreased on
10-30%, CFP – increased on 5%-15% on initial and 5-10% on expanded samples, Tinyface – increased
on 10-15% on initial and 25-35% on expanded samples, LFW – decreased on 10-20% on initial sample
and increased on 25% on expanded sample, AgeDB – increased on 10-20% on initial sample and
decreased on 5-10% on expanded sample. Also, after resolution conversion preserving the aspect ratio,
some of the images were not face features extractable.

4. Conclusion
This work is devoted to the research of information technology of face recognition and person
identification based on such methods as Haar features, Gabor wavelet transform, histograms of oriented
gradients (HOG) and local binary patterns in one-dimensional space (1DLBP). The purpose of the
research is to improve the performance of the algorithm underlying in the basis of information
technology by exploring the conditions of image sample formation and effect of image properties on
the algorithm efficiency.
To conduct the experiments there were selected several databases of face images. During the
research it was found that the performance of the algorithm is affected by the presence in the etalon and
test samples of images, in which it is difficult to localize face region due to such conditions of image
capturing as extreme angle of rotation of a subject’s head, excessive lighting, etc. Also, algorithm
performance can be reduced during its appliance on samples of images captured under unconstrained
conditions regarding the background, lighting, subject’s head position, camera position in relate to the
subject, and other physical settings. After extracting from the etalon and test samples of images with
unrecognizable face regions and expanding the etalon samples of image from databases that were
formed under unconstrained conditions, the accuracy identification rate of the algorithm was improved
for images from the Database of Faces on 7.5%, FERET – on 20%, CFP – on 27.5%, Tinyface – on
7.5%, LFW – on 45%, AgeDB – on 25%.
The next sets of experiments were performed with conversion of such image properties as format
and resolution with an aim to explore the possibility to reduce the variety of algorithm performance
results on samples of images from different databases. As a result of experiments, it was established
that format of images, to which the explored algorithm was applied, in individual cases affects the
efficiency - the identification accuracy rate increased on 5% after converting images from the Database
of Faces images to JPG format and decreased on 5% in case of expanded etalon sample of images from
LFW database. The conversion of resolution has also affected the algorithm performance. The results
for were increased on 5%-10% for samples of images from the Database of Faces, decreased on 5-35%
for samples from FERET, decreased on 10-30% for samples from SCface, increased on 5%-15% on
initial and 5-10% on expanded samples from CFP, increased on 10-15% on initial and 25-35% on
expanded samples from Tinyface, decreased on 10-20% on initial sample and increased on 25% on
expanded sample from LFW, increased on 10-20% on initial sample and decreased on 5-10% on
expanded sample from AgeDB.
The highest identification accuracy rate, which is 95%, was obtained on image sample of initial
images from SCface database and on image sample after reforming of the etalon image sample by
extracting images with unrecognizable face region.

5. References
[1] I. Adjabi, A. Ouahabi, A. Benzaoui and A. Taleb-Ahmed, “Past, Present, and Future of Face
Recognition: A Review,” Electronics. 2020; 9(8):118, doi: 10.3390/electronics9081188.
[2] A, K. Jain, K. Nandakumar and A. Ross, “50 years of biometric research: Accomplishments,
challenges, and opportunities,” Pattern Recognition Letters, vol. 79, 2016, pp. 80-105, ISSN 0167-
8655. doi: https://doi.org/10.1016/j.patrec.2015.12.013.
[3] C. Lucia, G. Zhiwei and N. Michele, “Biometrics for Industry 4.0: a survey of recent applications,”
Journal of Ambient Intelligence and Humanized Computing, 14, 2023, pp. 11239–11261. doi:
10.1007/s12652-023-04632-7

41
[4] Implement Face Recognition on Autonomous sUAS for Identification and Intelligence-Gathering.
URL: https://www.sbir.gov/node/2217727
[5] O. Bychkov, K. Merkulova, Y. Zhabska and A. Shatyrko, “Development of information
technology for person identification in video stream”, II International Scientific Symposium
“Intelligent Solutions” (IntSol-2021), CEUR Workshop Proceedings, vol. 3018, 2021, pp. 70–80.
URL: https://ceur-ws.org/Vol-3018/Paper_7.pdf
[6] T. Mantoro, M. A. Ayu and Suhendi, “Multi-Faces Recognition Process Using Haar Cascades and
Eigenface Methods,” 2018 6th International Conference on Multimedia Computing and Systems
(ICMCS), Rabat, Morocco, 2018, pp. 1-5. doi: 10.1109/ICMCS.2018.8525935.
[7] R. R. Isnanto, A. A. Zahra, A. L. Kurniawan and I. P. Windasari, “Face Recognition System Using
Feature Extraction Method of 2-D Gabor Wavelet Filter Bank and Distance-Based Similarity
Measures,” 2022 Seventh International Conference on Informatics and Computing (ICIC),
Denpasar, Bali, Indonesia, 2022, pp. 1-4. doi: 10.1109/ICIC56845.2022.10007016.
[8] J.R. Movellan. Tutorial on Gabor, 2002. URL: https://inc.ucsd.edu/mplab/tutorials/gabor.pdf
[9] A. Benzaoui and A. Boukrouche. Face Analysis, Description and Recognition using Improved
Local Binary Patterns in One Dimensional Space. Journal of Control Engineering and Applied
Informatics, Vol. 16, No. 4, pp. 52-60, 2014.
[10] B. Attallah, A. Serir, Y. Chahir, A. Boudjelal. Histogram of gradient and binarized statistical image
features of wavelet subband-based palmprint features extraction. J. Electron. Imag. 26(6) 063006,
November 8, 2017, doi: 10.1117/1.JEI.26.6.063006.
[11] The Database of Faces, AT&T Laboratories Cambridge. URL: https://cam-
orl.co.uk/facedatabase.html
[12] Face Recognition Technology (FERET). URL: https://www.nist.gov/programs-projects/face-
recognition-technology-feret
[13] M. Grgic, K. Delac and S. Grgic, “SCface - surveillance cameras face database,” Multimedia Tools
and Applications Journal, Vol. 51, No. 3, February 2011, pp. 863-879.
[14] SCface — Surveillance Cameras Face Database. URL: https://www.scface.org
[15] Celebrities in Frontal-Profile in the Wild. URL: http://www.cfpw.io
[16] Z. Cheng, X. Zhu, S. Gong. TinyFace: Face Recognition in Native Low-resolution Imagery. URL:
https://qmul-tinyface.github.io/index.html
[17] Labeled Faces in the Wild. URL: http://vis-www.cs.umass.edu/lfw/index.html
[18] S. Moschoglou, A. Papaioannou, C. Sagonas, J. Deng, I. Kotsia and S. Zafeiriou, “AgeDB: The
First Manually Collected, In-the-Wild Age Database,” 2017 IEEE Conference on Computer Vision
and Pattern Recognition Workshops (CVPRW), Honolulu, HI, USA, 2017, pp. 1997-2005. doi:
10.1109/CVPRW.2017.250.
[19] V. Martsenyuk, O. Bychkov, K. Merkulova and Y. Zhabska, “Exploring Image Unified Space for
Improving Information Technology for Person Identification,” in IEEE Access, vol. 11, pp. 76347-
76358, 2023, doi: 10.1109/ACCESS.2023.3297488.