Skip to main content
SpringerLink
Log in

Haar descriptors preliminary sampling

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

The selection of meaningful features for training computer vision solutions is the most important part of a robust framework construction. A huge amount of possible features with different parameters makes this task chalenging. We have developed a preliminary procedure of sampling of Haar descriptors for more effective learning of the binary classifier. A dataset and boosting weights are used to sample a data driven subset of descriptors from the vast space of all potential candidates, using the Kullback-Leibler divergence as a metric. Our aim was to create a simple technique which makes Haar features mining more reasonable and helps to reach higher learning rates, and further to investigate the practical usage of this data-driven approach. The proposed technique can be used for improvement of learning rates during the training process of cascade Haar classifiers with the usage of the AdaBoost framework. The developed data-driven sampling procedure can help to improve learning rates up to 34% depending on the dataset type. Additionally, the research clarifies the influence of the ‘complexity’ of dataset samples on learning effectiveness and provides practical recommendations for a reasonable choice of the initial size of descriptors’ list.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12

Similar content being viewed by others

References

  1. AbdelRaouf A, Salama D (2018) Handwritten signature verification using Haar Cascade classifier approach. In: 13th International conference on computer engineering and systems (ICCES), https://doi.org/10.1109/ICCES.2018.8639437

  2. Besnassi M, Neggaz N, Benyettou A (2020) Face detection based on evolutionary Haar filter. Pattern Anal Applic 23(1):309–330. https://doi.org/10.1007/s10044-019-00784-5

    Article  Google Scholar 

  3. Bishop MC (2006) Pattern recognition and machine learning. Springer, Berlin

    MATH  Google Scholar 

  4. Blum AL, Langley P (1997) Selection of relevant features and examples in machine learning. Amficial Intell 97(1-2):245–271. https://doi.org/10.1016/S0004-3702(97)00063-5

    Article  MathSciNet  MATH  Google Scholar 

  5. Chen D, Jin G, Lu L, Tan L, Wei W (2018) Infrared image vehicle detection based on Haar-like feature. In: IEEE 3rd advanced information technology, electronic and automation control conference. https://doi.org/10.1109/IAEAC.2018.8577211

  6. Cheng R, Zhang Y, Wang G, Zhao Y, Khusravsho R (2017) Haar-Like multi-granularity texture features for pedestrian detection. Int J Image Graph 17(4):1750023. https://doi.org/10.1142/S0219467817500231

    Article  Google Scholar 

  7. Cobos-May C, Uc-Cetina V, Brito-Loeza C, Martin-Gonzalez A (2015) A convex set based algorithm to automatically generate Haar-Like features. Int J Comput Sci 2(2):64–70

    Google Scholar 

  8. Dandashy T, Hassan ME, Bitar A (2019) Enhanced face detection based on Haar-Like and MB-LBP features. Int J Eng Manag Res 9(4). https://doi.org/10.31033/ijemr.9.4.17

  9. Dollár P, Tu Z, Tao H, Belongie S (2007) Feature mining for image classification. In: IEEE conference on computer vision and pattern recognition. https://doi.org/10.1109/CVPR.2007.383046

  10. Dollár P, Wojek C, Schiele B, Perona P (2009) Pedestrian detection: a benchmark. In: Conference on computer vision and pattern recognition. https://doi.org/10.1109/CVPR.2009.5206631

  11. Duan S, Wang X, Wan W (2013) The LogitBoost based on joint feature for face detection. In: Seventh international conference on image and graphics. https://doi.org/10.1109/ICIG.2013.97

  12. Freund Y (2001) An adaptive version of the boost by majority algorithm. Mach Learn 43:293–318. https://doi.org/10.1023/A:1010852229904

    Article  MATH  Google Scholar 

  13. Girsh R (2015) Fast R-CNN. In: IEEE international conference on computer vision (ICCV). https://doi.org/10.1109/ICCV.2015.169

  14. Hoang V-D, Vavilin A, Jo K-H (2012) Pedestrian detection approach based on modified Haar-like features and AdaBoost. In: International conference on control, automation and systems

  15. Jardi S, Saidallah M, El Alaoui AEB, El Fergougui A (2018) Moving vehicle detection using Haar-like LBP and a machine learning Adaboost algorithm. In: IEEE international conference on image processing, applications and systems (IPAS https://doi.org/10.1109/IPAS.2018.8708898)

  16. Krawiec K, Bhanu B (2003) Visual learning by evolutionary feature synthesis. In: Twentieth international conference on machine learning

  17. Leng L, Zhang J, Khan K, Chen X (2010) Dynamic weighted discrimination power analysis: a novel approach for face and palmprint recognition in DCT domain. Phys Sci Int J 5(17):467–471. https://doi.org/10.1109/ICTC.2010.5674791

    Article  Google Scholar 

  18. Lienhart R, Maydt J (2002) An extended set of Haar-like features for rapid object detection. In: International conference on image processing. https://doi.org/10.1109/ICIP.2002.1038171

  19. Lisani J-L, Ramis S (2019) A contrario detection of faces with a short cascade of classifiers. In: Image processing on line. https://doi.org/10.5201/ipol.2019.272

  20. Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu C-Y, Berg AC (2016) SSD: single shot multiBox detector. In: European conference on computer vision (ECCV). https://doi.org/10.1007/978-3-319-46448-_2

  21. Liu C, Shum HY (2003) Kullback-leibler boosting. Comput Vis Pattern Recognit:587–594. https://doi.org/1109/CVPR.2003.1211407

  22. Luo A, An F, Zhang X, Mattausch HJ (2018) A hardware-efficient recognition accelerator using Haar-like feature and SVM classifier. IEEE Access 7:14472–14487. https://doi.org/10.1109/ACCESS.2019.2894169

    Article  Google Scholar 

  23. Mita T, Kaneko T, Hori O (2005) Joint Haar-like features for face detection. In: Tenth IEEE international conference on computer vision (ICCV). https://doi.org/10.1109/ICCV.2005.129

  24. Munder S, Gavrila DM (2006) An experimental study on pedestrian classification. IEEE Trans Pattern Anal Mach Intell 28(11):1863–1868. https://doi.org/10.1109/TPAMI.2006.217

    Article  Google Scholar 

  25. Naido S, Porle R (2020) Face detection using colour and Haar features for indoor surveillance. In: IEEE 2nd international conference on artificial intelligence in engineering and technology (IICAIET). https://doi.org/10.1109/IICAIET49801.2020.9257813

  26. Oualla M, Ounachad R, Sadiq A (2020) The fast integration of a rotated rectangle applied to the rotated Haar-like features for rotated objects detection. Int J Adv Trends Comput Sci Eng 9(3):4055–4062. https://doi.org/10.30534/ijatcse/2020/232932020

    Article  Google Scholar 

  27. Papagergiou C, Poggio T (2000) A trainable system for object detection. Int J Comput Vis 38(1):15–33. https://doi.org/10.1023/A:1008162616689

    Article  MATH  Google Scholar 

  28. Pavania S-K, Delgadoa D, Frangia AF (2010) Haar-like features with optimally weighted rectangles for rapid object detection. Pattern Recogn 43(1):160–172. https://doi.org/10.1016/j.patcog.2009.05.011

    Article  Google Scholar 

  29. Pham M-T, Cham T-J (2007) Fast training and selection of Haar features using statistics in boosting-based face detection. In: IEEE 11th international conference on computer vision. https://doi.org/10.1109/ICCV.2007.4409038

  30. Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: unified, real-time object detection. In: IEEE conference on computer vision and pattern recognition (CVPR). https://doi.org/10.1109/CVPR.2016.91

  31. Rezaei M, Ziaei Nafchi H, Morales S (2014) Global Haar-like features: a new extension of classic Haar features for efficient face detection in noisy images. Image and Video Technol. https://doi.org/10.1007/978-3-642-53842-1_26

  32. Saha S, Kanagasingam Y (2019) Haar pattern based binary feature descriptor for retinal image registration. Digit Image Comput: Tech Appl (DICTA). https://doi.org/10.1109/DICTA47822.2019.8946021

  33. Savio MMD, Deepa T, Bonasu A, Anurag TS (2021) Image processing for face recognition using HAAR, HOG, and SVM algorithms. J Phys Conf Ser 1964(6):062023. https://doi.org/10.1088/1742-6596/1964/6/062023

    Article  Google Scholar 

  34. Shujuan S, Zhize X, Xingang W, Guan H, Wenqi W, De X (2015) Real-time vehicle detection using Haar-SURF mixed features and gentle AdaBoost classifier. In: The 27th Chinese Control and Decision Conference (CCDC). https://doi.org/10.1109/CCDC.2015.7162227

  35. Srithar S, Mettildha IM, Baskaran P, Maheswaran T (2021) Improved Haar cascade feature extraction and access control framework for rich internet applications. J Phys Conf Ser 1916(1):012019. https://doi.org/10.1088/1742-6596/1916/1/012019

    Article  Google Scholar 

  36. Sugiharto A, Harjoko A, Suharto S (2020) Indonesian traffic sign detection based on haar-PHOG features and SVM classification. Int J Smart Sens Intell Syst 13(1):1–15. https://doi.org/10.21307/ijssis-2020-026

    Article  Google Scholar 

  37. Viola P, Jones M (2003) Fast multi-view face detection. In: IEEE conference on computer vision and pattern recognition (CVPR)

  38. Viola P, Jones MJ (2004) Robust real-time face detection. Int J Comput Vis 57:137–154. https://doi.org/10.1023/B:VISI.0000013087.49260.fb

    Article  Google Scholar 

  39. Wachs J, Stern H, Edan Y, Gillam M, Feied C, Smith M, Handler J (2005) A real-time hand gesture system based on evolutionary search. In: Tenth genetic and evolutionary computation conference

  40. Wei Y, Tian q, Guo T (2015) An improved pedestrian detection algorithm integrating Haar-Like features and HOG descriptors. Adv Mech Eng. https://doi.org/10.1155/2013/546206

  41. Zhang S, Bauckhage C, Cremers AB (2014) Informed Haar-like features improve pedestrian detection. In: IEEE conference on computer vision and pattern recognition (CVPR). https://doi.org/10.1109/CVPR.2014.126

  42. Zhang B, Ye G, Wang Y, Wang W, Xu J, Herman G, Yang J (2009) Informative frequent assembled feature for face detection. In: IEEE international conference on image processing (ICIP). https://doi.org/10.1109/ICIP.2009.5413663

  43. Zhou C, Wu M, Lam S-K (2017) Fast and accurate pedestrian detection using dual-stage group cost-sensitive RealBoost with vector form filters. In: ACM multimedia conference. https://doi.org/10.1145/3123266.3123303

Download references

Acknowledgements

The research has been done as part of PProduct Inc CV research program. We would like to thank Michael Vulikh and Nadia Mezenina for their support.

Author information

Authors and Affiliations

  1. P-Product Inc, Kharkiv, Ukraine

    Andrii Dashkov & Oleksii Khaleiev

Authors
  1. Andrii Dashkov
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Oleksii Khaleiev
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Andrii Dashkov.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Dashkov, A., Khaleiev, O. Haar descriptors preliminary sampling. Multimed Tools Appl 82, 819–837 (2023). https://doi.org/10.1007/s11042-022-13204-4

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-022-13204-4

Keywords

Search

Navigation