Data Segmentation in Object Recognition Tasks
Abstract
The purpose of the research is to study the possibility of accelerating the processes of object recognition in images using algorithms for segmenting data according to specified parameters using a device for simplified hardware pattern recognition.
Methods: the method of dividing the frame, with the help of a device simplified hardware pattern recognition, into the contours most suitable for the description of the sought objects is used. Data segmentation is performed by a device capable of forming an array of coordinates that define areas corresponding to the specified parameters. The device accepts a number of parameters, such as: color range; contour shape; the size; permissible deviations in the shape and size of the contour. The usual scheme of the object recognition process is modified by preliminary processing outside the final system, due to which the need for such stages as "Primary processing" and "Formation of features" disappears.
Results: data segmentation speeds up the process of recognizing objects on a frame by the end system, due to a decrease in the search area. The speed superiority result depends on the number of objects found and their size. In a simple example given, the result of increasing the speed can be up to 8 times.
Conclusion: recognition algorithms will be able to perform processing much faster, due to a significant reduction in the working area, relative to the original frame. To obtain a good result, it is necessary to carefully select the recognition algorithm itself for the final system, or paint over the area of the frame that was not determined by the device as the desired one. This is necessary, since most recognition algorithms do not know how to work with this approach.
About the Authors
S. V. Degtyarev
Southwest State University
Russian Federation
Russian Federation
Sergey V. Degtyarev, Dr. of Sci. (Engineering), Professor
50 Let Oktyabrya str. 94, Kursk 305040
E. A. Kriushin
Southwest State University
Russian Federation
Russian Federation
Evgeny A. Kriushin, Post-Graduate Student
50 Let Oktyabrya str. 94, Kursk 305040
D. V. Nikulin
Southwest State University
Russian Federation
Russian Federation
Denis V. Nikulin, Post-Graduate Student
50 Let Oktyabrya str. 94, Kursk 305040
E. N. Ivanova
Southwest State University
Russian Federation
Russian Federation
Elena N. Ivanova, Cand. of Sci. (Engineering)
50 Let Oktyabrya str. 94, Kursk 305040
References
1. Degtyarev S. V., Lysenko Ya. A., Ivanova E. N. Sintez struktur ustroistv kontrolya pokazanii panelei priborov [Synthesis of structures of indication control devices dashboards]. Informatsionno-izmeritel'nye i upravlyayushchie sistemy = Information-Measuring and Control Systems, 2015, vol. 13, no. 6, pp. 20-25.
2. Degtyarev S. V., Lysenko Ya. A., Ivanova E. N., eds. Optiko-elektronnoe ustroistvo parallel'nogo kontrolya pokazanii paneli priborov [Optical-electronic device for parallel control of instrument panel readings]. Informatsionno-izmeritel'nye i upravlyayushchie sistemy = Information-Measuring and Control Systems, 2016, vol. 14, no. 10, pp. 31-33.
3. Kriushin E. A. [Hardware accelerator of image processing for image recognition system]. Globalizatsiya nauki i tekhniki v usloviyakh krizisa. Materialy XXIX Vserossiiskoi nauchno-prakticheskoi konferentsii (15 marta 2021g.) [Globalization of science and technology in a crisis. Materials of the XXIX All-Russian Scientific and Practical Conference (March 15, 2021)]. Rostov-on-Don, Publishing House of the Southern University IUBiP, 2021, pt. 1. 314 p. (In Russ.)
4. Trudy ISA RAN: Sistemnoe modelirovanie. Naukometriya i upravlenie naukoi. Raspoznavanie obrazov [Proceedings of ISA RAS. System modeling. Scientometrics and Science Management. Pattern Recognition ]; ed. by S. V. Emelyanov. Moscow, Lenand Publ., 2015, 104 p.
5. Informatsionnye tekhnologii i vychislitel'nye sistemy: Obrabotka informatsii i analiz dannykh. Programmnaya inzheneriya. Matematicheskoe modelirovanie. Prikladnye aspekty informatiki [Information technology and computing systemsю Information processing and data analysis. Software engineering. Mathematical modeling. Applied Aspects of Informatics]; ed. by S. V. Emelyanov. Moscow, Lenand Publ., 2015. 104 p.
6. Informatsionnye tekhnologii i vychislitel'nye sistemy. Vychislitel'nye sistemy. Komp'yuternaya grafika. Raspoznavanie obrazov. Matematicheskoe modelirovanie [Information technology and computing systems. Computing systems. Computer graphics. Pattern recognition. Mathematical modeling]; ed. by S. V. Emelyanov. Moscow, Lenand Publ., 2015. 100 p.
7. Trudy ISA RAN: Matematicheskie modeli sotsial'no-ekonomicheskikh protsessov. Modelirovanie kharakteristik deyatel'nosti otraslevykh i regional'nykh podsistem. Dinamich- eskie sistemy. Matematicheskie problemy dinamiki neodnorodnykh sistem: Informatsionnye tekhnologii [Proceedings of ISA RAS. Mathematical models of socio-economic processes. Modeling the performance characteristics of sectoral and regional subsystems. Dynamical systems. Mathematical problems of the dynamics of inhomogeneous systems. Information technologies]; ed. by S. V. Emelyanov. Moscow, Lenand Publ., 2015, 112 p.
8. Dudarev V. A. Metody raspoznavaniya obrazov v komp'yuternom konstruirovanii neorganicheskikh soedinenii [Methods of pattern recognition in computer design of inorganic compounds]. Moscow, Synergy Publ., 2014. 325 p.
9. Avtomaticheskoe upravlenie i vychislitel'naya tekhnika: sbornik [Automatic control and computer technology. Collection]. Moscow, Mechanical Engineering Publ., 2016, is. 10. 256 p.
10. Astakhova I., Mishchenko V., Krasnoyarov A. Modeli raspoznavaniya obrazov na osnove nechetkikh neironnykh setei [Pattern recognition models based on fuzzy neural networks]. Moscow, Palmarium Academic Publishing, 2013. 104 p.
11. Kapitonova T. A. Neirosetevoe modelirovanie v raspoznavanii obrazov. Filosofsko- metodicheskie aspekty [Neural network modeling in pattern recognition. Philosophical and methodological aspects]. Moscow, Mir Publ., 2019. 549 p.
12. Shmaglit L. A., Golubev M. N., Ganin A. N., Khryashchev V. V. [Gender classification by facial image]. Tsifrovaya obrabotka signalov i ee primenenie: doklady XIV Mezhdu- narodnoi. konferentsii (DSPA-2012). [Digital signal processing and its application (DSPA- 2012). Reports of the XIV International Conference], Moscow, 2012, vol. 2, 425 p. (In Russ.)
13. Milenky A. V. Klassifikatsiya signalov v usloviyakh neopredelennosti. Statisticheskie metody samoobucheniya v raspoznavanii obrazov [Classification of signals in conditions of uncertainty. Statistical methods of self-learning in pattern recognition]. Moscow, Soviet Radio Publ., 2017. 328 p.
14. Tsvetkov A. A., Shorokh D. K., Zubareva M. G., eds. [Object recognition algorithms]. Tekhnicheskie nauki: problemy i perspektivy: materialy IV Mezhdunarodnoi nauchnoi kon- ferentsii (g. Sankt-Peterburg, iyul' 2016 g.) [Technical sciences. Problems and prospects. Materials of the IV Intern. Scientific. Conf. (St. Petersburg, July 2016)]. St. Petersburg, Own Publishing House, 2016, pp. 20-28. (In Russ.)
15. Avtomaticheskoe upravlenie i vychislitel'naya tekhnika: sbornik [Automatic control and computer technology. Collection]. Moscow, Mechanical Engineering Publ., 2015, is. 10. 256 p.
16. Loktev A. A., Alfimtsev A. N., Loktev D. A. Algoritm raspoznavaniya ob"ektov [Object recognition algorithm]. VestnikMGSU = NewspaperMGSU, 2012, no. 5, рр. 194-201.
17. Eliseeva I. I., Rukavishnikov V. O. Gruppirovka, korrelyatsiya, raspoznavanie obrazov (statisticheskie metody klassifikatsii i izmereniya svyazei) [Grouping, correlation, pattern recognition (statistical methods of classification and measurement of connections)]. Moscow, Lights Publ., 2016. 144 p.
18. Boyko I. A., Guryanov R. A. Raspoznavanie ob"ektov na osnove videosignala, polu- chennogo s kamery, ustanovlennoi na podvizhnoi platforme [Object recognition based on the video signal received from a camera installed on a mobile platform].Molodoi uchenyi = Young Scientist, 2013, no. 6 (53), pp. 34-36.
19. Rabotyagov A. Osnovy raspoznavaniya obrazov [Fundamentals of pattern recognition]. Moscow, LAP Lambert Academic Publishing, 2014. 273 p.
20. Fukunaga K. Vvedenie v statisticheskuyu teoriyu raspoznavaniya obrazov [Introduction to the statistical theory of pattern recognition]. Moscow, Nauka Publ., 2013. 368 p.
Review
For citations:
Degtyarev S.V., Kriushin E.A., Nikulin D.V., Ivanova E.N. Data Segmentation in Object Recognition Tasks. Proceedings of the Southwest State University. Series: IT Management, Computer Science, Computer Engineering. Medical Equipment Engineering. 2021;11(2):76-86. (In Russ.)
Views:
125
Email this article 