Abstract
In digital images, edges characterize object boundaries, so edge detection remains a crucial stage in numerous applications. To achieve this task, many edge detectors have been designed, producing different results, with various qualities of segmentation. Indeed, optimizing the response obtained by these detectors has become a crucial issue, and effective contour assessment assists performance evaluation. In this paper, several referenced-based boundary detection evaluations are detailed, pointing out their advantages and disadvantages, theoretically and through concrete examples of image edges. Then, a new normalized supervised edge map quality measure is proposed, comparing a ground truth contour image, the candidate contour image and their associated spatial nearness. The effectiveness of the proposed distance measure is demonstrated theoretically and through several experiments, comparing the results with the methods detailed in the state-of-the-art. In summary, compared to other boundary detection assessments, this new method proved to be a more reliable edge map quality measure.
Similar content being viewed by others
References
Abdou IE, Pratt WK (1979) Quantitative design and evaluation of enhancement/thresholding edge detectors. Proc IEEE 67(5):753–763
Baddeley AJ (1992) An error metric for binary images. Robust Comp Vision: Qual Vis Algorithm:59–78
Basseville M (1989) Distance measures for signal processing and pattern recognition. Signal Proc 18(4):349–369
Baudrier E, Nicolier F, Millon G, Ruan S (2008) Binary-image comparison with local-dissimilarity quantification. Pattern Recogn 41(5):1461–1478
Boaventura IAG, Gonzaga A (2009) Method to evaluate the performance of edge detector, Brazilian Symposium on Comp Graphics and Image Proceedungs
Bourennane E, Gouton P, Paindavoine M, Truchetet F (2002) Generalization of Canny–Deriche filter for detection of noisy exponential edge. Signal Proc 82(10):1317–1328
Bowyer K, Kranenburg C, Dougherty S (2001) Edge detector evaluation using empirical ROC curves, Comp Vis Image Understand:77–103
Canny J (1986) A computational approach to edge detection. IEEE Trans Pattern Anal Mach Intel 6:679–698
Chabrier S, Laurent H, Rosenberger C, Emile B (2008) Comparative study of contour detection evaluation criteria based on dissimilarity measures. EURASIP J Image Vid Proc 2008:1–13
Demigny D (2002) On optimal linear filtering for edge detection. IEEE Trans Image Proc 11(7):728– 737
Deriche R (1987) Using Canny’s criteria to derive a recursively implemented optimal edge detector. Int J Comput Vis 1:167–187
Deutsch E, Fram JR (1978) A quantitative study of the orientation bias of some edge detector schemes. IEEE Trans Comput 27(3):205–213
Dubuisson MP, Jain AK (1994) A modified Hausdorff distance for object matching, 12th IAPR. Int Conf Pattern Recogn 1:566–568
Fernández-Garcıa NL, Medina-Carnicer R, Carmona-Poyato A, Madrid-Cuevas FJ, Prieto-Villegas M (2003) Characterization of empirical discrepancy evaluation measures. Pattern Recogn Lett 25(1):35–47
Freeman WT, Adelson EH (1991) The design and use of steerable filters. IEEE TPAMI 13:89–906
Geusebroek JM, Smeulders A, van de Weijer J (2002) Fast anisotropic gauss filtering. ECCV 2002:99–112
Gimenez J, Martinez J, Flesia AG (2014) Unsupervised edge map scoring: A statistical complexity approach. Comp Vis Image Understand 122:131–142
Goumeidane AB, Khamadja M, Belaroussi B, Benoit-Cattin H, Odet C (2003) New discrepancy measures for segmentation evaluation. IEEE ICIP 2:411–414
Grigorescu C, Petkov N, Westenberg MA (2003) Contour detection based on nonclassical receptive field inhibition. IEEE Trans Image Proc 12(7):729–739
Haralick RM (1984) Digital step edges from zero crossing of second directional derivatives. IEEE Trans Pattern Anal Mach Intel 6(1):58–68
Heath MD, Sarkar S, Sanocki T, Bowyer KW (1997) A robust visual method for assessing the relative performance of edge-detection algorithms. IEEE Trans Pattern Anal Mach Intel 19(12):1338–1359
Hemery B, Laurent H, Emile B, Rosenberger C (2010) Comparative study of localization metrics for the evaluation of image interpretation systems. J Elec Imaging 19(2):023017–023017
Hou X, Yuille A, Koch C (2013) Boundary detection benchmarking: Beyond f-measures. IEEE Conference on Comparative Vision and Pattern Recognition:2123–2130
Huttenlocher DP, Rucklidge WJ (1993) A multi-resolution technique for comparing images using the Hausdorff distance. IEEE Trans Pattern Anal Mach Intel 15(9):850–863
Jacob M, Unser M (2004) Design of steerable filters for feature detection using canny-like criteria. IEEE TPAMI 26(8):1007–1019
Falah RK, Bolon PW, Cocquerez JP, Region-Region A (1994) Region-edge cooperative approach of image segmentation. IEEE Int Conf Image Proc 3:470–474
Köthe U (2007) Reliable low-level image analysis. Habilitation thesis
Laligant O, Truchetet F, Meriaudeau F (2007) Regularization preserving localization of close edges. IEEE Signal Proc Lett 14(3):185–188
Lee SU, Chung SY, Park RH (1990) A comparative performance study of several global thresholding techniques for segmentation. CVGIP 52(2):171–190
Lopez-Molina C, Bustince H, Fernandez J, Couto P, De Baets B (2010) A gravitational approach to edge detection based on triangular norms. Pattern Recogn 43(11):3730–3741
Lopez-Molina C, De Baets B, Bustince H (2013) Quantitative error measures for edge detection. Pattern Recogn 46(4):1125–1139
Lopez-Molina C, Galar M, Bustince H, De Baets B (2014) On the impact of anisotropic diffusion on edge detection. Pattern Recogn 47(1):270–281
Magnier B, Comby F, Strauss O, Triboulet J, Demonceaux C (2010) Highly specific pose estimation with a catadioptric omnidirectional camera. IEEE Int Conf Imaging Syst Techn:229–233
Magnier B, Montesinos P, Diep D (2011) Texture removal by pixel classification using a rotating filter. In: IEEE International Conference on Acoustics, Speech, and Signal Proceedings, pp 1097–1100
Magnier B, Montesinos P, Diep D (2011) Fast anisotropic edge detection using gamma correction in color images. IEEE Int Symp Image Signal Proc Anal:212–217
Magnier B, Aberkane A, Borianne P, Montesinos P, Jourdan C (2014) Multi-scale crest line extraction based on half gaussian kernels. IEEE Int Conf Acoust Speech Signal Proc:5105–5109
Magnier B, Le A, Zogo A (2016) A quantitative error measure for the evaluation of roof edge detectors. IEEE Int Conf Imaging Syst Techn:429–434
Marr D, Hildreth E (1980) Theory of edge detection. Proc Royal Soc Lond Series B, Biol Sci 207(1167):187–217
Martin DR, Fowlkes CC, Malik J (2004) Learning to detect natural image boundaries using local brightness, color, and texture cues. IEEE Trans Pattern Anal Mach Intel 26(5):530–549
Odet C, Belaroussi B, Benoit-Cattin H (2002) Scalable discrepancy measures for segmentation evaluation. IEEE Int Conf Image Proc 1:785–788
Otsu N (1979) A threshold selection method from gray-level histograms. IEEE Trans Syst Man Cybern 9:62–66
Panetta K, Gao C, Agaian S, Nercessian S (2014) Non-reference medical image edge map measure. J Bio Imaging 2014:1–12
Panetta K, Gao C, Agaian S, Nercessian S (2016) A new reference-based edge map quality measure. IEEE Trans Syst Man Cybern: Syst 46(11):1505–1517
Papari G, Petkov N (2011) Edge and line oriented contour detection State of the art. Image Vis Comput 29(2):79–103
Paumard J (1997) Robust comparison of binary images. Pattern Recogn Lett 18 (10):1057–1063
Peli T, Malah D (1982) A study of edge detection algorithms. CGIP 20(1):1–21
Pinho AJ, Almeida LB (1995) Edge detection filters based on artificial neural networks. In: International Conference on Image Analysis and Proceedings. Springer, Berlin Heidelberg, pp 159–164
Román-Roldán R, Gómez-Lopera JF, Atae-Allah C, Martinez-Aroza J, Luque-Escamilla PL (2001) A measure of quality for evaluating methods of segmentation and edge detection. Pattern Recogn 34(5):969–980
Rosenfeld A, Thurston M (1971) Edge and curve detection for visual scene analysis. IEEE Trans Comp 100(5):562–569
Shen J, Castan S (1986) An optimal linear operator for edge detection. IEEE CVPR 86:109–114
Sneath P, Sokal R (1973) Numerical taxonomy The principles and practice of numerical classification
Strasters KC, Gerbrands JJ (1991) Three-dimensional image segmentation using a split, merge and group approach. Pattern Recogn Lett 12(5):307–325
Sobel IE (1970) Camera models and machine perception. PhD Thesis, Stanford University, Stanford
Torre V, Poggio TA (1986) On edge detection. IEEE Trans Pattern Anal Mach Intel 8(2):147–163
Usamentiaga R, García DF, López C, González D (2006) A method for assessment of segmentation success considering uncertainty in the edge positions. EURASIP J Appl Signal Proc 2006:207–207
Venkatesh S, Rosin PL (1995) Dynamic threshold determination by local and global edge evaluation. Comp Vis Graph Image Proc 57(2):146–160
Wang Z, Bovik AC, Sheikh HR, Simoncelli EP (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Pattern Anal Mach Intel 13(4):600–612
Wilson DL, Baddeley AJ, Owens RA (1997) A new metric for grey-scale image comparison. Int J Comp Vis 24(1):5–17
Yasnoff WA, Galbraith W, Bacus JW (1978) Error measures for objective assessment of scene segmentation algorithms. Anal Quant Cytol 1(2):107–121
Yitzhaky Y, Peli E (2003) A method for objective edge detection evaluation and detector parameter selection. IEEE Trans Pattern Anal Mach Intel 25(8):10271033
Zhao C, Shi W, Deng Y (2005) A new Hausdorff distance for image matching. Pattern Recogn Lett 26(5):581–586
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Magnier, B. Edge detection: a review of dissimilarity evaluations and a proposed normalized measure. Multimed Tools Appl 77, 9489–9533 (2018). https://doi.org/10.1007/s11042-017-5127-6
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-017-5127-6