Abstract
Edge detection plays an important role in many computer vision systems. In this paper, we propose a novel application agnostic algorithm for prediction of probabilities based on the contextual information available and then apply the algorithm for estimating the probability of pixels belonging to an edge using surrounding pixel values as local contexts. We then proceed to test different image transformations as input layers, such as the Canny edge detector. We propose two different architectures, one single layered and one multilayered, which approach the scaling problem by creating scaled side outputs and combining them via a logistic regression layer. We tested our approach on the BSDS500 edge detection dataset with optimistic results.
References
Gaonkar B, Hovda D, Martin N et al (2016) Deep learning in the small sample size setting: cascaded feed forward neural networks for medical image segmentation. Proc SPIE 9785:97852I
Milletari F, Navab N, Ahmadi S (2016) V-Net: fully convolutional neural networks for volumetric medical image segmentation. In: IEEE fourth international conference on 3D vision, pp 565–571
Fram JR, Deutsch ES (1975) On the quantitative evaluation of edge detection schemes and their comparison with human performance. IEEE Trans Comput C-24:6:616–628
Arbelaez P, Maire M, Fowlkes C, Malik J (2011) Contour detection and hierarchical image segmentation. IEEE TPAMI 33(5):898–916
Dollár P, Zitnick LC (2015) Fast edge detection using structured forests. IEEE Trans Pattern Anal Mach Intell 37(8):1558–1570
Xie S, Tu Z (2017) Holistically-nested edge detection. Proc IEEE Int J Comput Vis 125(1):3–18
Liu Y, Lew MS (2016) Learning relaxed deep supervision for better edge detection. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 231–240
Liu Y, Cheng MM et al (2019) Richer convolutional features for edge detection. In: IEEE transactions on pattern analysis and machine intelligence; http://mftp.mmcheng.net/Papers/19PamiEdge.pdf. Accessed 05 Nov 2018
Fu F, Wang C et al (2018) An improved adaptive edge detection algorithm based on Canny. In: Proceedings of SPIE 10827 icOPEN. Accessed 24 Jul 2018
Guadaa C, Edwin Zarrazolab et al (2018) A novel edge detection algorithm based on a hierarchical graph-partition approach. J Intell Fuzzy Syst 34:1875–1892
Minka T (2017) A comparison of numerical optimizers for logistic regression. https://tminka.github.io/papers/logreg/minka-logreg.pdf. Accessed 05 Feb 2017
Naftaly U, Intrator N, Horn D (1999) Optimal ensemble averaging of neural networks. Netw Comput Neural Syst 8:3
Liu Y, Yao X (1999) Ensemble learning via negative correlation. Neural Netw 12(10):1399–1404
Long PM, Servedio RA (2010) Random classification noise defeats all convex potential boosters. Mach Learn 78(3):287–304
http://www.burtleburtle.net/bob/hash/doobs.html. Accessed 05 Feb 2017
http://www.isthe.com/chongo/tech/comp/fnv/index.html. Accessed 05 Feb 2017
Mattern C (2012) Mixing strategies in data compression. In: Proceedings of the 22nd data compression conference (DCC), pp 337–346
Mahoney M (2005) Adaptive weighing of context models for lossless data compression. http://mattmahoney.net/dc/cs200516.pdf. Accessed 05 Feb 2017
http://www.byronknoll.com/cmix.html. Accessed 05 Nov 2018
Wang Y, Zhao X et al (2018) Deep crisp boundaries. From boundaries to higher-level tasks. arXiv preprint arXiv:1801.02439
Xu D, Ouyang W et al (2017) Learning deep structured multi-scale features using attention-gated CRFs for contour prediction. In: Advances in neural information processing system, pp 3961–3970
Yu Z, Feng C et al (2017) CASENet: deep category-aware semantic edge detection. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 21–26
Yang J, Price B et al (2016) Object contour detection with a fully convolutional encoder-decoder network. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 193–202
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Dorobanţiu, A., Brad, R. A novel contextual memory algorithm for edge detection. Pattern Anal Applic 23, 883–895 (2020). https://doi.org/10.1007/s10044-019-00808-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10044-019-00808-0