Promising Research and Development Results in the Field of Image and Speech Signal Processing
https://doi.org/10.35596/1729-7648-2024-22-2-55-69
Abstract
An analysis of the prospects for the development of technologies for processing images and speech signals is presented. The main results in these areas obtained in recent years in the relevant scientific schools of Belarusian State University of Informatics and Radioelectronics are presented. It is shown that the use of machine learning technologies in combination with methods of digital processing of images and speech signals can significantly increase the efficiency of systems for their recognition and classification.
About the Authors
D. S. Likhachov
Belarusian State University of Informatics and Radioelectronics
Belarus
Belarus
Cand. of Sci., Associate Professor, Associate Professor at Computer Engineering Department
J. Ma
Belarusian State University of Informatics and Radioelectronics
Belarus
Belarus
Assistant at the Department of Infocommunication Technologies
N. A. Petrovsky
Belarusian State University of Informatics and Radioelectronics
Belarus
Belarus
Cand. of Sci., Associate Professor, Associate Professor at Computer Engineering Department
I. S. Azarov
Belarusian State University of Informatics and Radioelectronics
Belarus
Belarus
Dr. of Sci. (Tech.), Associate Professor, Head of Computer Engineering Department
V. Yu. Tsviatkou
Belarusian State University of Informatics and Radioelectronics
Belarus
Belarus
Dr. of Sci. (Tech.), Professor, Head of the Department of Infocommunica tion Technologies
220013, Minsk, P. Brovki St., 6
Tel.: +375 17 293-84-08
References
1. GII. Global Information. Available: https://www.giiresearch.com/ (Accessed 29 January 2024).
2. Fortune Business Insights Information. Available: https://www.fortunebusinessinsights.com/ (Accessed 29 January 2024).
3. Blum H. (1967). A Transformation for Extracting New Descriptors of Shape. Cambridge, MIT Press, MA. 362–380.
4. Saha P. K., Borgefors G., Sanniti di Baja G. (2016) A Survey on Skeletonization Algorithms and Their Applications. Pattern Recognition Letter. 76, 3–12. DOI: 10.1016/j.patrec.2015.04.006.
5. Ogniewicz R. L., Kübler O. (1995) Hierarchic Voronoi Skeletons. Pattern Recognition. 28, 343–359.
6. Leymarie F., Levine M. D. (1992) Simulating the Grassfire Transform Using an Active Contour Model. IEEE Transactions on Pattern Analysis and Machine Intelligence. 14, 56–75.
7. Saha P. K., Borgefors G., Sanniti di Baja G. (2017) Skeletonization: Theory, Methods, and Applications. Academic Press. London.
8. Bai X., Latecki L. J., Liu W. Y. (2007) Skeleton Pruning by Contour Partitioning with Discrete Curve Evolution. IEEE Trans. Pattern Anal. Mach. Intell. 29 (3), 449–462. DOI: 10.1109/TPAMI.2007.59.
9. Wei S., Xiang B. A. I., Xingwei Y., Jan L. L. (2013) Skeleton Pruning as Trade-Off Between Skeleton Simplicity and Reconstruction Error. Sci. China Inf. Sci. 56, 1–14. DOI: 10.1007/s11432-012-4715-3.
10. Liu H., Wu Z. H., Zhang X., Hsu D. F. (2013) A Skeleton Pruning Algorithm Based on Information Fusion. Pattern Recognit. Lett. 34 (10), 1138–1145. DOI: 10.1016/j.patrec.2013.03.013.
11. Siyu G., Pingping H., Zhigang L., He W., Min L. (2019) A Skeleton Pruning Method Based on Saliency Sorting. 14th IEEE International Conference on Electronic Measurement & Instruments. Changsha, China. 593–599. DOI: 10.1109/ICEMI46757.2019.9101710.
12. Latecki L. J., Lakämper R. (1999) Convexity Rule for Shape Decomposition Based on Discrete Contour Evolution. Comput. Vis. Image Underst. 73 (3), 441–454. DOI: 10.1006/cviu.1998.0738.
13. Latecki L. J., Lakämper R. (1999) Polygon Evolution by Vertex Deletion. Lect. Notes Comput. Sci. (Including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), Springer, Berlin, Heidelberg. 1682, 398–409. DOI: 10.1007/3-540-48236-9_35.
14. Latecki L. J., Lakämper R. (1999) Shape Similarity Measure Based on Correspondence of Visual Parts. IEEE Trans. Pattern Anal. Mach. Intell. 22 (10), 1185–1190. DOI: 10.1109/34.879802.
15. Ma J., Ren X. H., Tsviatkou V. Yu. (2020) A Novel Fast Iterative Parallel Thinning Algorithm. Proceedings of the 2020 4th International Conference on Vision, Image and Signal Processing, New York, NY, USA. Article 7, 1–5. DOI: 10.1145/3448823.3448836.
16. Choi W., Lam K., Siu W. (2003) Extraction of the Euclidean Skeleton Based on a Connectivity Criterion. Pattern Recognition. 36, 721–729. DOI: 10.1016/S0031-3203(02)00098-5.
17. Ma J., Ren X., Tsviatkou V. Yu., Kanapelka V. K. (2021) A Novel Fully Parallel Skeletonization Algorithm. Pattern Analysis and Applications. 1–20. DOI: 10.1007/s10044-021-01039-y.
18. Ma J., Ren X., Li H., Li W., Tsviatkou V. Y., Boriskevich A. A. (2023) Noise-Against Skeleton Extraction Framework and Application on Hand Gesture Recognition. IEEE Access. 11, 9547–9559. DOI: 10.1109/ACCESS.2023.3240313.
19. Chin R. T., Wan H. K., Stover D., Iverson R. (1987) A One-Pass Thinning Algorithm and Its Parallel Implementation. Computer Vision, Graphics and Image Processing. 40, 30–40. DOI: 10.1016/0734-189X(87)90054-5.
20. Ma J., Tsviatkou V. Y., Boriskevich A. A. (2023) Hand Gesture Recognition Based on Skeletal Image Properties. Open Semantic Technologies for Intelligent Systems: Collection of Scientific Papers. (7), 247–256.
21. Petrovsky N. A., Rybenkov E. V., Petrovsky A. A. (2018) Two-Dimensional Non-Separable Quaternionic Paraunitary Filter Banks. Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA). 120–125.
22. Rybenkov E. V., Petrovsky N. A. (2019) 2D Non-Separable Integer Implementation of Paraunitary Filter Bank Based on the Quaternionic Multiplier Block-Lifting Structure. 27th European Signal Processing Conference (EUSIPCO). 1494–1499.
23. Rybenkov E. V., Petrovsky N. A. (2019) Design of Non-Separable Multidimensional Filter Banks in Quaternionic Algebra. Digital Signal Processing and its Applications: Proc. of 21 International Conference (DSPA’2019). 2, 368–373.
24. Likhachov D. S., Vashkevich M. I., Petrovsky N. A., Azarov E. S. (2023) Small-Size Spectral Features for Machine Learning in Voice Signal Analysis and Classification Tasks. Informatics. 20 (1), 102–112. DOI: 10.37661/1816-0301-2023-20-1-102-112 (in Russian).
25. Likhachov D. S., Vashkevich M. I., Petrovsky N. A., Azarov I. S. (2022) Generative Method of Obtaining Spectral Envelopes for Speech Signal Analysis and Processing Tasks. Medelectronics-2022. Means of Medical Electronics and New Medical Technologies: Collection of Scientific Articles XI Intern. Scientific and Technical Conference, Minsk, Dec. 8–9. Minsk, Belarusian State University of Informatics and Radioelectronics. 281–283 (in Russian).
26. Likhachov D. S., Vashkevich M. I., Petrovsky N. A., Azarov E. S. (2023) Combined Method for Informative Feature Selection for Speech Pathology Detection. Doklady BGUIR. 21 (4), 110–117. DOI: 10.35596/1729-7648-2023-21-4-110-117 (in Russian).
Review
For citations:
Likhachov D.S., Ma J., Petrovsky N.A., Azarov I.S., Tsviatkou V.Yu. Promising Research and Development Results in the Field of Image and Speech Signal Processing. Doklady BGUIR. 2024;22(2):55-69. (In Russ.) https://doi.org/10.35596/1729-7648-2024-22-2-55-69
Views: 127
Email this article 