Optimization methods for face recognition algorithmes

I.P. Sitkov, M.M. Glybovets

Abstract


The paper examines the main drawbacks of modern face recognition algorithms: low processing speed, high sensitivity to image quality and face positioning. A division into three approaches to face recognition algorithms optimization is proposed: optimization of feature weights, algorithm hyperparameters, and constructing an optimal distributed system architecture. Examples of the application of Particle Swarm Optimization, Cuckoo Search, Simulated Annealing, and genetic algorithms to overcome the mentioned limitations in existing algorithms are provided. The study demonstrates the advantages and disadvantages of these optimization methods and identifies promising directions for further research in face identification methods optimization using genetic algorithms.

Prombles in programming 2025; 1: 74-81


Keywords


optimization methods; genetic algorithm; convolutional neural networks; face recognition algorithms

References


Zhang, Y. and Yan, L. (2023) "Face recognition algorithm based on particle swarm optimization and image feature compensation", SoftwareX, 22, p. 101305. CrossRef

Fang, S. et al. (2017) "Face recognition using weber local circle gradient pattern method", Multimedia Tools and Applications, 77(2), pp. 2807-2822. CrossRef

Zafeiriou, S., Zhang, C. and Zhang, Z. (2015) "A survey on face detection in the wild: Past, present and future", Computer Vision and Image Understanding, 138, pp. 1-24. CrossRef

Oloyede, M.O., Hancke, G.P. and Myburgh, H.C. (2020) "A review on face recognition systems: recent approaches and challenges", Multimedia Tools and Applications, 79(37-38), pp. 27891-27922. CrossRef

Poli, R., Kennedy, J. and Blackwell, T. (2007) "Particle swarm optimization", Swarm Intelligence, 1(1), pp. 33-57. CrossRef

Gandomi, A.H., Yang, X.-S. and Alavi, A.H. (2012) "Erratum to: Cuckoo search algorithm: a metaheuristic approach to solve structural optimization problems", Engineering With Computers, 29(2), p. 245. CrossRef

Malhotra, P. and Kumar, D. (2017) "An optimized face recognition system using Cuckoo search", Journal of Intelligent Systems, 28(2), pp. 321-332. CrossRef

Yan, L., Zhang, Yanhu and Zhang, Yanjun (2023) "A fast face recognition system based on annealing algorithm to optimize operator parameters", The Imaging Science Journal, 71(4), pp. 323-330. CrossRef

Huang, J., Shang, Y. and Chen, H. (2019) "Improved Viola-Jones face detection algorithm based on HoloLens", EURASIP Journal on Image and Video Processing, 2019(1). CrossRef

Li, W. et al. (2023) "Face recognition model optimization research based on embedded platform", IEEE Access, 11, pp. 58634-58643. CrossRef

Oroceo, P.P. et al. (2022) "Optimizing Face Recognition Inference with a Collaborative Edge-Cloud Network", Sensors, 22(21), p. 8371. CrossRef

Karlupia, N. et al. (2023) "A genetic algorithm based optimized convolutional neural network for face recognition,' International Journal of Applied Mathematics and Computer Science, 33(1). CrossRef

Loussaief, S. and Abdelkrim, A. (2018) "Convolutional Neural Network HyperParameters Optimization based on Genetic Algorithms", International Journal of Advanced Computer Science and Applications, 9(10). CrossRef

Sun, Y. et al. (2020) "Automatically designing CNN architectures using the genetic algorithm for image classification", IEEE Transactions on Cybernetics, 50(9), pp. 3840-3854. CrossRef




DOI: https://doi.org/10.15407/pp2025.01.074

Refbacks

  • There are currently no refbacks.