Abstract
We propose a general algorithm that treats cascade training as a tree search process working according to Dijkstra’s algorithm in contrast to our previous solution based on the branch-and-bound technique. The reason behind the algorithm change is reduction of training time. This change does not affect in anyway the quality of the final classifier. We conduct experiments on cascades trained to become face or letter detectors with Haar-like features or Zernike moments being the input information, respectively. We experiment with different tree sizes and different branching factors. Results confirm that training times of obtained cascades, especially for large heavily branched trees, were reduced. For small trees, the previous technique can sometimes achieve better results but the difference is negligible in most cases.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
Initial value of \(\widehat{E}^*\) is set to \(\infty \), after first cascade satisfying (A, D) requirements finish its training, \(\widehat{E}^*\) represents its expected number of features.
References
Andrean, M.N., et al.: Comparing haar cascade and yoloface for region of interest classification in drowsiness detection. Jurnal Media Informatika Budidarma 8(1), 272–281 (2024)
Bernabe, J.A., Dylan O. Catapang, J., Valiente, L.D.: Application of haar cascade classifier for kitchen safety monitoring. In: 2023 9th International Conference on Advanced Computing and Communication Systems (ICACCS), vol. 1, pp. 343–348 (2023)
de Campos, T.E., et al.: Character recognition in natural images. In: Proceedings of the International Conference on Computer Vision Theory and Applications, Lisbon, Portugal, pp. 273–280 (2009)
Di, J., Gao, R.: Research on railway transportation route based on dijkstra algorithm. In: Atiquzzaman, M., Yen, N., Xu, Z. (eds.) Big Data Analytics for Cyber-Physical System in Smart City, pp. 255–260. Springer, Singapore (2022). https://doi.org/10.1007/978-981-16-7469-3_28
Dijkstra, E.W.: A note on two problems in connexion with graphs. Numer. Math. 1(1), 269–271 (1959)
Gharge, S., Patil, A., Patel, S., Shetty, V., Mundhada, N.: Real-time object detection using haar cascade classifier for robot cars. In: 2023 4th International Conference on Electronics and Sustainable Communication Systems (ICESC), pp. 64–70 (2023)
Ghorbel, A., Ben Amor, N., Abid, M.: GPGPU-based parallel computing of viola and jones eyes detection algorithm to drive an intelligent wheelchair. J. Signal Process. Syst. 94(12), 1365–1379 (2022)
Rasolzadeh, B., et al.: Response binning: improved weak classifiers for boosting. In: IEEE Intelligent Vehicles Symposium, pp. 344–349 (2006)
Sychel, D., Klęsk, P., Bera, A.: Branch-and-bound search for training cascades of classifiers. In: Krzhizhanovskaya, V.V., et al. (eds.) ICCS 2020. LNCS, vol. 12140, pp. 18–34. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-50423-6_2
Sychel, D., Klęsk, P., Bera, A.: Relaxed per-stage requirements for training cascades of classifiers. In: Frontiers in Artificial Intelligence and Applications – ECAI 2020, vol. 325, pp. 1523–1530. IOS Press (2020)
University of Essex: Face Recognition Data (1997). https://cswww.essex.ac.uk/mv/allfaces/faces96.html. Accessed 11 May 2019
Usilin, S.A., Slavin, O.A., Arlazarov, V.V.: Memory consumption and computation efficiency improvements of viola-jones object detection method for remote sensing applications. Pattern Recognit. Image Anal. 31(3), 571–579 (2021)
Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: Conference on Computer Vision and Pattern Recognition (CVPR 2001), pp. 511–518. IEEE (2001)
Viola, P., Jones, M.: Robust real-time face detection. Int. J. Comput. Vision 57(2), 137–154 (2004)
Wang, J., Yu, X., Zong, R., Lu, S.: Evacuation route optimization under real-time toxic gas dispersion through CFD simulation and Dijkstra algorithm. J. Loss Prev. Process Ind. 76, 104733 (2022)
Zhou, Y., Huang, N.: Airport AGV path optimization model based on ant colony algorithm to optimize Dijkstra algorithm in urban systems. Sustain. Comput. Inform. Syst. 35, 100716 (2022)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Sychel, D., Bera, A., Klęsk, P. (2024). Cascade Training as a Tree Search with Dijkstra’s Algorithm. In: Franco, L., de Mulatier, C., Paszynski, M., Krzhizhanovskaya, V.V., Dongarra, J.J., Sloot, P.M.A. (eds) Computational Science – ICCS 2024. ICCS 2024. Lecture Notes in Computer Science, vol 14833. Springer, Cham. https://doi.org/10.1007/978-3-031-63751-3_17
Download citation
DOI: https://doi.org/10.1007/978-3-031-63751-3_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-63753-7
Online ISBN: 978-3-031-63751-3
eBook Packages: Computer ScienceComputer Science (R0)