Pattern Analysis and Applications

, Volume 21, Issue 1, pp 221–231 | Cite as

EDTriangles: a high-speed triangle detection algorithm with a false detection control

  • Selcan Kaplan Berkaya
  • Serkan Gunal
  • Cuneyt Akinlar
Short paper


We present a high-speed method for triangular object detection. The proposed method utilizes the recently developed, real-time edge segment detection algorithm, Edge Drawing; hence, the name EDTriangles, which consists of a detection stage and a validation stage. In the detection stage, EDTriangles extracts edge segments from the image using Edge Drawing and converts these edge segments into line segments, which are then converted into line pairs according to the angles between the line segments and the distance between their endpoints. Next, the line pairs are combined together using some heuristics to generate many triangle candidates, some of which are valid detections and some invalid. Finally, in the validation stage the candidate triangles are validated using the Helmholtz principle and number of false alarms computation to eliminate false detections. Experimental results show that EDTriangles runs very fast, detects various types of triangular objects ranging from narrow to wide-angled triangles and offers a higher detection performance compared to some of the well-known triangle detection algorithms found in the literature.


Triangular object detection Geometrical shape detection Edge drawing Helmholtz principle 


  1. 1.
    delaEscalera A, Moreno LE, Salichs MA, Armingol JM (1997) Road traffic sign detection and classification. IEEE Trans Ind Electron 44(6):848–859. doi: 10.1109/41.649946 CrossRefGoogle Scholar
  2. 2.
    Gao DS, Zhou J (2000) Car license plates detection from complex scene. In: Proceedings of the 5th international conference on signal processing, vol 2, pp 1409–1414. doi: 10.1109/ICOSP.2000.891808
  3. 3.
    Maldonado-Bascon S, Lafuente-Arroyo S, Gil-Jimenez P, Gomez-Moreno H, Lopez-Ferreras F (2007) Road-sign detection and recognition based on support vector machines. IEEE Trans Intell Transp Syst 8(2):264–278. doi: 10.1109/Tits.2007.895311 CrossRefMATHGoogle Scholar
  4. 4.
    Ruta A, Li YM, Liu XH (2010) Real-time traffic sign recognition from video by class-specific discriminative features. Pattern Recognit 43(1):416–430. doi: 10.1016/j.patcog.2009.05.018 CrossRefMATHGoogle Scholar
  5. 5.
    Xu S (2009) Robust traffic sign shape recognition using geometric matching. IET Intell Transp Syst 3(1):10–18. doi: 10.1049/iet-its:20070058 CrossRefGoogle Scholar
  6. 6.
    Zaklouta F, Stanciulescu B (2014) Real-time traffic sign recognition in three stages. Robot Auton Syst 62(1):16–24. doi: 10.1016/j.robot.2012.07.019 CrossRefGoogle Scholar
  7. 7.
    Zhu SD, Zhang Y, Lu XF (2005) Detection for triangle traffic sign based on neural network. In: IEEE international conference on vehicular electronics and safety, pp 25–28. doi: 10.1109/ICVES.2005.1563608
  8. 8.
    Yuan X, Guo J, Hao X, Chen H (2015). Traffic sign detection via graph-based ranking and segmentation algorithms. IEEE Trans Syst Man Cybern. doi: 10.1109/TSMC.2015.242777 (In press)
  9. 9.
    Mogelmose A, Liu D, Trivedi MM (2015) Detection of U.S. traffic signs. IEEE Trans Intell Transp Syst. doi:  10.1109/TITS.2015.2433019(In press)
  10. 10.
    Barnes N, Loy G, Shaw D (2010) The regular polygon detector. Pattern Recognit 43(3):592–602. doi: 10.1016/j.patcog.2009.09.008 CrossRefMATHGoogle Scholar
  11. 11.
    Garlipp T, Muller CH (2006) Detection of linear and circular shapes in image analysis. Comput Stat Data Anal 51(3):1479–1490. doi: 10.1016/j.csda.2006.04.022 MathSciNetCrossRefMATHGoogle Scholar
  12. 12.
    He JP, Ma Y (2009) Triangle detection based on windowed Hough transform. In: Proceedings of 7th international conference on wavelet analysis and pattern recognition, pp 95–100. doi: 10.1109/ICWAPR.2009.5207484
  13. 13.
    Liu H, Wang Z (2014) PLDD: point-lines distance distribution for detection of arbitrary triangles, regular polygons and circles. J Vis Commun Image Represent 25(2):273–284. doi: 10.1016/j.jvcir.2013.10.002 CrossRefGoogle Scholar
  14. 14.
    Liu YX, Goto S, Ikenaga T (2006) An MRF model based algorithm of triangular shape object detection in color images. Int J Inf Technol 12(2):55–65Google Scholar
  15. 15.
    Zhu Y, Quingzhi Z (2011) Rectangle detection by the chain-code tracing. In: International conference on electrical and control engineering, Yichang, pp 759–762. doi: 10.1109/ICECENG.2011.6057576
  16. 16.
    Topal C, Akinlar C (2012) Edge Drawing: a combined real-time edge and segment detector. J Vis Commun Image Represent 23(6):862–872. doi: 10.1016/j.jvcir.2012.05.004 CrossRefGoogle Scholar
  17. 17.
    Desolneux A, Moisan L, Morel JM (2004) Gestalt theory and computer vision. In: Seeing, Thinking and knowing, Springer, Netherlands, pp 71–101CrossRefGoogle Scholar
  18. 18.
    Desolneux A, Moisan L, Morel JM (2008) From gestalt theory to image analysis: a probabilistic approach. Springer Science & Business Media, New York, USA, pp 31–45Google Scholar
  19. 19.
    Douglas DH, Peucker KT (1973) Algorithms for the reduction of the number of points required to represent a digitized line or its caricature. Cartographica Int J Geogr Inf Geovisualization 10(2):112–122CrossRefGoogle Scholar
  20. 20.
    Ramer U (1972) An iterative procedure for the polygonal approximation of plane curves. Comput Vis Graph Image Process 1(3):244–256. doi: 10.1016/S0146-664X(72)80017-0 CrossRefGoogle Scholar
  21. 21.
    Akinlar C, Topal C (2012) Edpf: a real-time parameter-free edge segment detector with a false detection control. Int J Pattern Recognit Artif Intell 26(1). doi: 10.1142/S0218001412550026
  22. 22.
    Akinlar C, Topal C (2011) EDLines: a real-time line segment detector with a false detection control. Pattern Recognit Lett 32(13):1633–1642. doi: 10.1016/j.patrec.2011.06.001 CrossRefGoogle Scholar
  23. 23.
    Akinlar C, Topal C (2013) EDCircles: a real-time circle detector with a false detection control. Pattern Recognit 46(3):725–740. doi: 10.1016/j.patcog.2012.09.020 CrossRefGoogle Scholar
  24. 24.
    Desolneux A, Moisan L, Morel JM (2000) Meaningful alignments. Int J Comput Vis 40(1):7–23. doi: 10.1023/A:1026593302236 CrossRefMATHGoogle Scholar
  25. 25.
    von Gioi RG, Jakubowicz J, Morel JM, Randall G (2008) On straight line segment detection. J Math Imaging Vis 32(3):313–347. doi: 10.1007/s10851-008-0102-5 MathSciNetCrossRefGoogle Scholar
  26. 26.
    von Gioi RG, Jakubowicz J, Morel JM, Randall G (2010) LSD: a fast line segment detector with a false detection control. IEEE Trans Pattern Anal 32(4):722–732. doi: 10.1109/Tpami.2008.300 CrossRefGoogle Scholar
  27. 27.
    Bradski G, Kaehler A (2008) Learning OpenCV: computer vision with the OpenCV library. O’Reilly Media Inc, pp 241–251Google Scholar
  28. 28.
    Houben S, Stallkamp J, Salmen J, Schlipsing M, Igel C (2013) Detection of traffic signs in real-world images: The German traffic sign detection benchmark. In: The 2013 international joint conference on neural networks (IJCNN), Dallas, TX, pp 1–8. doi: 10.1109/IJCNN.2013.6706807 Google Scholar
  29. 29.
    Kaplan Berkaya S, Gunduz H, Ozsen O, Akinlar C, Gunal S (2016) On circular traffic sign detection and recognition. Expert Syst Appl 48:67–75. doi: 10.1016/j.eswa.2015.11.018 CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London 2017

Authors and Affiliations

  • Selcan Kaplan Berkaya
    • 1
  • Serkan Gunal
    • 1
  • Cuneyt Akinlar
    • 1
  1. 1.Department of Computer EngineeringAnadolu UniversityEskisehirTurkey

Personalised recommendations