Adaptive Technique for Brightness Enhancement of Automated Knife Detection in Surveillance Video with Deep Learning


Detecting knives in surveillance videos are very urgent for public safety. In general, the research in identifying dangerous weapons is relatively new. Knife detection is a very challenging task because knives vary in size and shape. Besides, it easily reflects lights that reduce the visibility of knives in a video sequence. The reflection of light on the surface of the knife and the brightness on its surface makes the detection process extremely difficult, even impossible. This paper presents an adaptive technique for brightness enhancement of knife detection in surveillance systems. This technique overcomes the brightness problem that faces the steel weapons and improves the knife detection process. It suggests an automatic threshold to assess the level of frame brightness. Depending on this threshold, the proposed technique determines if the frame needs to enhance its brightness or not. Experimental results verify the efficiency of the proposed technique in detecting knives using the deep transfer learning approach. Moreover, the most four famous models of deep convolutional neural networks are tested to select the best in detecting knives. Finally, a comparison is made with the-state-of-the-art techniques, and the proposed technique proved its superiority.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9


  1. 1.

    Grega, M. et al.: Automated recognition of firearms in surveillance. In: IEEE International Multi-Disciplinary Conference on Cognitive Methods in Situation Awareness and Decision Support (CogSIMA), San Diego (2013)

  2. 2.

    Kumar, R.T.; Verma, G.K.: A computer vision based framework for visual gun detection using SURF. In: Proceedings of International Conference on Electrical, Electronics, Signals, Communication and Optimization (EESCO,2015) (2015)

  3. 3.

    Kumar, RT; Verma, G.K.: A computer vision based framework for visual gun detection using Harris Interest Point Detector. In: Eleventh International Multi-Conference on Information Processing-2015 (IMCIP-2015) in ElSevier, vol. 54, pp. 703–712 (2015)

  4. 4.

    Dhulekar, P.A., et al.: Motion estimation for human activity surveillance. In: International Conference Emerging Trends & Innovation in ICT (ICEI,2017), Pune, India (2017)

  5. 5.

    Arslan, A.N.; Hempelmann, C.F., et al.: Threat assessment using visual hierarchy and conceptual firearms ontology. Opt. Eng. 54(5), 105–109 (2015)

    Article  Google Scholar 

  6. 6.

    Darker, l. et al.: Can CCTV reliably detect gun crime?. In: Proceedings of IEEE, United States of America, United States of America (2007)

  7. 7.

    Blechko, A. et al.: Skills in detecting gun carrying from CCTV. In: Proceedings of IEEE, Prague, Czech Republic (2009)

  8. 8.

    Darker, I.T.; Gale, A.G.; Blechko, A.: CCTV as an automated sensor for firearms detection: Human-derived performance as a precursor to automatic recognition. In: Proceedings of the International Society for Optical Engineering, (ISOE,2008), Cardiff, Wales, United Kingdom (2008)

  9. 9.

    Xiao, Z.; Lu, X.; Yan, J.; Wu, L.; Luyao: Automatic detection of concealed pistols using passive millimeter wave imaging. In: 2015 IEEE International Conference on Imaging Systems and Techniques (IST), 1–4, IEEE, 2015

  10. 10.

    Zywicki, M. et al.: Knife detection as a subset of object detection approach based on Haar cascades. In: Proceedings of 11th International Conference on Pattern Recognition and Information Processing, Minsk, Belarus (2011)

  11. 11.

    Kmiec, M.; Glowacz, A.: An approach to Robust Visual Knife Detection (MG&V,2011). Mach. Graphics Vis. 20(2), 215–227 (2011)

    Google Scholar 

  12. 12.

    Kmieć, M. et al.: Towards robust visual knife detection in images: active appearance models initialised with shape-specific interest points. In: Proceedings of International Conference on Multimedia Communications, Services and Security., Krakow, Poland (2012)

  13. 13.

    Maksimova, A.: Knife detection scheme based on possibilistic shell clustering. In: International Conference on Multimedia Communications, Services and Security, Springer, Berlin, Heidelberg (2013)

  14. 14.

    Glowacz, A., et al.: Visual detection of knives in security applications using active appearance models. Multimed. Tools Appl. Springer 74(12), 4253–4267 (2015)

    Article  Google Scholar 

  15. 15.

    Maksimova, A., et al.: Fuzzy classification method for knife detection problem. Int. Conf. Multimed. Commun., Serv. Secu., Springer 429, 159–169 (2014)

    Google Scholar 

  16. 16.

    Kmieć, M.; Glowacz, A.: Object detection in security applications using dominant edge directions. Pattern Recogn. Lett., in Elsevier 52, 72–79 (2015)

    Article  Google Scholar 

  17. 17.

    Grega, M., et al.: Automated detection of firearms and knives in a CCTV image. Sensors 16(1), 47–63 (2016)

    Article  Google Scholar 

  18. 18.

    Vajhala, R. et al.: Weapon detection in surveillance camera images, Department of Applied Signal Processing Blekinge Institute of Technology, Karlskrona, Sweden (2016)

  19. 19.

    Buckchash, H.; Raman, B.: A robust object detector: Application to detection of visual knives. In: Proceedings of the IEEE International Conference on Multimedia and Expo Workshops (ICMEW) 2017 (2017)

  20. 20.

    LeCun, Y.; Kavukcuoglu, K.; Farabet, C.: Convolutional networks and applications in vision. In: Proceedings of 2010 IEEE International Symposium on Circuits and Systems (2010)

  21. 21.

    Yanming Guo, Yu.; Liu, A.O.; Lao, S.: Deep learning for visual understanding: A review. Neurocomputing 187, 27–48 (2016)

    Article  Google Scholar 

  22. 22.

    Liua, W.; Wanga, Z.; Liua, X.; Ze, N.: A survey of deep neural network architectures and their applications. Neurocomputing 234, 11–26 (2017)

    Article  Google Scholar 

  23. 23.

    Haridas, R.; Jyothi, R.L.: Convolutional neural networks: A comprehensive survey. Int. J. Appl. Eng. Res. 14(3), 780–789 (2019)

    Article  Google Scholar 

  24. 24.

    Olmos, R.; Tabik, S.; Herrera, F.: Automatic handgun detection alarm in videos using deep learning. Neurocomputing 275, 66–72 (2018)

    Article  Google Scholar 

  25. 25.

    Verma, G.K.; Dhillon, A.: A handheld gun detection using Faster R-CNN deep learning. In: Proceedings of the 7th International Conference on Computer and Communication Technology, pp. 84–88 (2017)

  26. 26.

    Al-Shoukry, S.: An automatic hybrid approach to detect concealed weapons using deep learning. ARPN J. Eng. Appl. Sci. 12(16), 4736–4741 (2017)

    Google Scholar 

  27. 27.

    Castillo, A.; Tabik, S.; Pérez, F.: Brightness guided preprocessing for automatic cold steel weapon detection in surveillance videos with deep learning. Neurocomputing 330, 151–161 (2019)

    Article  Google Scholar 

  28. 28.

    Noever, DA.; Noever, SEM.: “Knife and Threat Detectors,” white paper (2020)

  29. 29.

    Zhong-Qiu, Z.; Peng, Z.; Shou-tao, X.; Xindo: Object detection with deep learning: A review. IEEE Trans. Neural Netw. Learning Syst. 30(11), 3212–3232 (2019)

    Article  Google Scholar 

  30. 30.

    Alom, M.Z.; Taha, T.M.; Yakopcic, C.; Westberg, S.: “The History Began from AlexNet: A Comprehensive Survey on Deep Learning Approaches,”, pp. 1–39 (2018)

  31. 31.

    Torrey, L.; Shavlik, J.: Transfer learning. In: Appears in the Handbook of Research on Machine Learning Applications, published by IGI Global (2009)

  32. 32.

    Pan, S.J.; Yang, Q.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345–1359 (2009)

    Article  Google Scholar 

  33. 33.

    Nithya, M.D.K.: Comparison of contrast enhancement technique with partitioned iterated function system. Int. J. Sci. Eng. Res. 5(5), 167–172 (2014)

    Google Scholar 

  34. 34.

    Rahman, S.; Rahman, M.M.; Abdullah-Al-Wadud, M.; Al-Quaderi, G.D.; Shoyaib, M.: An adaptive gamma correction for image enhancement. EURASIP J. Image Video Process. SpringerOpen 2016(1), 1–13 (2016)

    Article  Google Scholar 

  35. 35.

    Pizer, S.M.; Johnston, R.E.; Eri, J.P.: Contrast-limited adaptive histogram equalization: speed and effectiveness. In: Proceedings of the First Conference on Visualization in Biomedical Computing, Atlanta, Georgia (1990).

  36. 36.

    Zuiderveld, K.: Contrast Limited Adaptive Histogram Equalization, p. 474–485. Academic Press Professional Inc, Singapore (1994)

    Google Scholar 

  37. 37.

    Reza, A.M.: Realization of the contrast limited adaptive histogram equalization (CLAHE) for real-time image enhancement. J. VLSI Signal Process. Syst. Signal, Image Video Technol. Springer 38(1), 35–44 (2004)

    Article  Google Scholar 

  38. 38.

    [Online]. Available:

  39. 39.

    [Online]. Available:

  40. 40.

    “Knife dataset for detection,” [Online]. Available:

  41. 41.

    “Knife detection,” [Online]. Available:

  42. 42.

    Tom, F.: An introduction to ROC analysis. Pattern Recogn. Lett. 27(8), 861–874 (2006)

    Article  Google Scholar 

Download references

Author information



Corresponding author

Correspondence to Mai K. Galab.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Galab, M.K., Taha, A. & Zayed, H.H. Adaptive Technique for Brightness Enhancement of Automated Knife Detection in Surveillance Video with Deep Learning. Arab J Sci Eng (2021).

Download citation


  • Knife detection
  • Smart video surveillance
  • Deep neural network
  • CNN
  • Weapon detection