Abstract. This article describes a developed application for identifying individuals in the Java programming language. For recognition of image templates, the OpenCV library was selected. Based on the methods that the OpenCV library classes offer, a program with a graphical user interface for detecting faces has been developed. Скачать в формате PDF
American Scientific Journal № ( 32) / 2019 21

for Land, Sea and Air, GT2009, June 8 -12, 2009,
Orlando, FL, USA.
Paşayev, A., Abdullayev, P. and Samedov, A .
(2018) Sıvı yakıtlı roket motorunun itme odasının
geliştirilmiş tasarım yöntemi , SAVTEK 2018,
9.Savunma Teknolojileri Kongresi, ODTÜ, Ankara,
27 -29 Haziran, 2018.
Rizkalla, O., Chinitz, W. and Erdos, J.I. (1990 )
Calculated Chemical and Vibrational Non equilibrium
Effects in Hypersonic Nozzles , Journal of propulsion
and power, pp.50 -57.
Sutton, G.P. (2010) Rocket Propulsion Elements ,
New York: John Wiley & Sons, Inc.,
Vasiliev, A.P., Kudryavtsev, V.M., Kuznets ov,
V.A., Kurpatenkov, V.D., Obelnitsky, A.M., Polyaev,
V.M., Poluyan, B.Y. (1983) Fundamentals of the
theory and calculation of liquid rocket engines,
Textbook. Edited by V.M. Kudryavtsev. Moscow,
High School, 3rd edition, revised and enlarged, 703 p.,
in russian.
Zebbiche, T. (2011) Stagnation temperature effect
on the supersonic axisymmetric minimum length
nozzle design with application for air , Adv. Space Res.
48 (10), 1656 –167 5.


Boranbayev S.N.,
Kabdulkarimov Y.Z.
Eurasian National University named after L.N. Gumilyov, Nur -Sultan

Abstract . This article describes a developed a pplication for identifying individuals in the Java programming
language. For recognition of image templates, the OpenCV library was selected. Based on the methods that the
OpenCV library classes offer, a program with a graphical user interface for detectin g faces has been developed.
Keywords: identification, recognition, image, pattern, processing, confidentiality, security.

Alan Kay said: “People who are really serious
about their software must create their own hardw are”
[1]. This expressio n is also suitable for ensuring your
own safety. A country that is truly serious about its own
security must create its own security software and
hardware. This means that each country must create its
own devices for the recognition , processing,
identifica tion and analysis of data obtained from video
and photo cameras of outdoor surveillance and other
monitoring devices for private and public sectors.Since,
if these devices were purchased abroad, this can lead to
information leakage, because the device can be
controlled remotely by the manufacturers of this
device. To ensure confidentiality and complete control
of security systems by your own government agencies,
you must create your own software for the recognition,
processing, ident ification and analysis o f information.
Therefore, creating an application for recognizing and
identifying certain image patterns, such as people's
faces, partially solves this problem.
2.Development of an application for facial
In the process of developing a progra m for face
recognition, the following sources were analyzed:
● Existing face recognition approaches used
by Google, Apple and Samsung to authenticate users
and face recognition in photos and videos; [2 -4]
● modern principle s of security systems for
face recogn ition and identification; [5,6]
● neural networks that are used to process and
analyze video and photos; [7.8]
Algorithms based on existing approaches have
been developed. A high -level Java programming
language is used t o create this application. The choice
of this particular programming language is that the
operating system of many devices, such as cell phones,
televisions, drones, camcorders, cameras is Android,
which is written in Java. Thus, it is possible to integrat e
the created program into a device th at uses Android.
Also programs written in Java are portable. After
compiling the program on the computer, it is possible
to run the bytecode of the program on all devices that
have a Java Virtual Machine. [9] Next, it was necessary
to choose a library that will recognize image templates.
Currently, Java does not have its own libraries for
recognizing image templates. A third -party OpenCV
library (Open Source Computer Vision Library, an
open -source computer vision librar y) was chosen - a
library of computer -vision algorithms, image
processing and general -purpose open -source numerical
algorithms. [10] Implemented in C / C ++, also
developed for Python, Java, Ruby, Matlab, Lua, and
other languages. It can be freely used for academic and
commercial purposes. The authors of this library are
Intel Corporation. [11] OpenCV includes the following
● image processing (filtering, geometric
transformations, color space conversion);
● input / output of images and videos, machine
learning models (SVM, decision trees, le arning with
● recognition and description of flat
● motion analysis and object tracking (optical
flow, motion patterns, background removal);
● detection of objects in the image (finding
faces using the Viola -Jones algorithm, recognizing
HOG people), calibrating the camera, searching for
stereo matching and 3D processing elements. [12]
Next, the task was to install and connect the
OpenCV library during application development. The
tricky part was conn ecting the library to the application.
Since there was no detailed user manual. However,

22 American Scientific Journal № ( 32) / 20 19
with the release of version 11 of Java, its own Java
library, JavaFx, a 3rd generation library for creating
programs with a graphical user interface, was not
included in the standard list of Java libraries and also
became third -party. Therefore, Java has written very
detailed instructions on how to connect and use third -
party libraries when developing programs in various
integrated development environments, including
Ec lipse, in which the application was de veloped.
These instructions were also suitable for
connecting OpenCV. After connecting and configuring
all the necessary components, the next stage began -
creating the application.
Based on the methods that the OpenCV library
classes offer, a program was developed with a graphical
user interface for detecting faces from a web camera
and photos.
The graphical interface of the program consists of
two buttons of the checkbox category for selecting face
detection algorithm s, Haar and Local Binary Templates
(LB P). Also, the Start camera button, which starts the
web camera only after selecting one of the recognition
algorithms. In the center is a frame in which video from
a web camera will be broadcast. The graphical interfac e
was created using SceneBuilder 2.0 ( Figure 1).

Figure 1. Creating a graphical user interface for the program using SceneBuilder 2.0.

The program itself consists of 3 classes
FaceDetection.java, FaceDetectionControl ler.java,
Utils.java and a FaceDetection.fxml file created using
SceneBuil der 2.0. These classes are illustrated in
Figures 2, 3, 4. The Utils.java class stores methods for
using OpenCV objects in JavaFX. The
FaceDetectionController.java class is responsib le for
the type of application, the application logic is also
implemented here. This class contains 7 class variables:
a button for turning the camera on and off, a frame
where the image from the camera is illustrated, 2
buttons for choosing the LBP or Haa r algorithms.
Methods for starting or stopping the camera
(startCamera), r eceiving a video stream (grabFrame),
an algorithm for controlling, detecting, tracking faces
(detectAndDisplay) are also stored. This method uses
an object of class Mat to obtain an image from the
camera. It then converts the image into an object for
LBP o r Haar algorithms. After this object has been
processed, coordinates are recorded. Next, rectangular
frames are created that will indicate faces in the camera
image. These rectangles are stored in the array. The
updateImageView method retrieves new frames
received from the camera. The haarSelected method
loads a trained set of algorithms for face recognition
based on the Haar algorithm. The lbpSelected method
loads a trained set of fa ce recognition algorithms based
on the LBP algorithm. These methods are th e main
methods of this program. The main class for the
application FaceDetection.java is a descendant of the
Application class creates and processes the main
window with its resource s (style, graphics). This
window processes the video stream and looks for a
person’s face using Haar or LBP algorithms. When a
person is found, it is framed. It consists of 2 methods:
start and main. The start method creates the main panel
of the program, on which there are buttons for starting
the camera, choosing Haar or LBP a lgorithms. There is
also a panel on which the image received from the
camera is located. This camera transmits and updates
the image in real time. Also, this method sets the
dimensio ns of the panels, the colors of the program.
The main method starts the pr ogram using the start
method. After the methods and classes are defined, they
can be used for training and forecasting [13 -16].
Figures [2 -4] show code fragments that implement
class es in Java.

American Scientific Journal № ( 32) / 2019 23

Figure 2. The FaceDetection.java class.

Figure 3. The Fac eDetectionController.java class.

24 American Scientific Journal № ( 32) / 20 19
Figure 4. The Utils.java class.

Figure 5 shows the operation of the application and finding faces using the LBP algorithm.

Figure 5. Face recognition using the LBP algorithm.

Figur e 6 shows the operation of the appli cation and finding faces using the Haar algorithm.

American Scientific Journal № ( 32) / 2019 25

Figure 6. Face recognition using the Haar algorithm.

3. Conclusion
The developed application can be used to identify
and locate people by scanning files from video cameras
that are located in public pla ces. Since this procedure
will be completely automatic, it can help to find certain
people, and will also save time for g overnment
Also, the application can be integrated into the
operating system of drones and used in search and
rescue operation s, in agriculture, and other fields.

1. talk at Creative Think seminar, 20 July 1982,
https://www.folklore .org/StoryView.py?project=
2. Arandjelovic, R., Gronat, P., Torii, A., Pajdla,
T., Sivic, J.: NetVLAD: CN N architecture for we еkly
supervised place recognition. In: CVPR (2016) 12
3. Avrithis, Y., Kalantidis, Y., Tolias, G.,
Spy rou, E.: Retrieving Landmark and Non -Landmark
Images from Community Photo Collections. In: ACM
Multimedia. pp. 153 –162 (2010)
4. Azizpour, H., Razavian, A.S., Sullivan, J.,
Maki, A., Carlsson, S.: From Generic to Specific Deep
Representations for Visual Reco gnition. In: CVPR
DeepVision Workshop (2015) 12
5. Baatz, G., Koeser, K., Chen, D., Grzeszczuk,
R., Pollefeys, M.: Handling urban location recognition
as a 2D homothetic problem. In: ECCV (2010)
6. Babenko, A., Lempitsky, V.: Aggregating
Local Deep Features for Image Retrieval. In: ICCV
7. Savitch, W.: Absolute Java. Pearson (2016)
8. Babenko, A., Slesarev, A., Chigorin, A.,
Lempitsky, V.: Neu ral codes for image retrieval. In:
ECCV (2014)
9. Bergamo, A., Sinha, S.N., Torresani, L.:
Leveraging Structure from Motion to Learn
Discriminative Codebooks for Scalable Landmark
Classification. In: CVPR. pp. 763 –770 (2013)
10. 1. Fundamentals of Computer Vision ,
Mubarak Shah, Computer Science Department,
University of C entral Florida, Orlando, FL 32816,
December 7, 2010.
11. The OpenCV 2.4.3 documentation, URL:
12. Mastering OpenCV with Practical Computer
Vision Projects, Published by Packt Publ ishing Ltd.
Livery Place, 35 Livery Street, Birmingham B3 2P B,
UK. ISBN 978 -1-84951 -782 -9.
13. Boranbayev, A., Boranbayev, S., Nurusheva,
A. Analyzing methods of recognition, classification
and development of a software system. Advances in
Intelligent Systems and Computing. –2018, Vol. 869,
pp. 690 -702.
14. Boranbayev, A., Shuitenov, G., Boranbayev,
S. The method of data analysis from social networks
using apache Hadoop. Advances in Intelligent Systems
and Computing. –2018, Vol. 558, pp. 281 -288.
15. Boranbayev, S., Nu rkas, A., Tulebayev, Y.,
Tashtai, B. Method of Processing Bi g Data. Advances
in Intelligent Systems and Computing. –2018, Vol.
738, pp. 757 -758.
16. Boranbayev A.S., Boranbayev S.N.,
Khassanova А.А. Comparative analysis of methods of
face detection and classif ication of images // Bulletin of
L.N. Gumilyov Eurasian Nati onal University №2,
2017. - P.71 -89.