Generic placeholder image

Recent Advances in Computer Science and Communications

Author(s): Mei Zhang*, Bin Xu and Jinghua Wen

DOI: 10.2174/2666255815666220513163140

DownloadDownload PDF Flyer Cite As
Deep Image Segmentation Using a Morphological Edge Operator

Article ID: e130522204780 Pages: 7

  • * (Excluding Mailing and Handling)

Explore Articles
About Journal
For Authors
For Editors
For Reviewers

Abstract

Background: Segmentation of deep images is a difficult, persistent problem in the computer vision field. This paper aimed to address the defects of traditional segmentation methods with deep images, presenting a deep image segmentation algorithm based on a morphological edge operator.

Methods: Deep image edge features were first extracted using three traditional edge operators; the edge and tip type jump edges were then extracted via a morphological edge operator, which was used to make the boundary connection; finally, to obtain more accurate segmentation results, skeletonizing was used to refine the image.

Results: Compared with traditional segmentation algorithms, the improved algorithm obtained smooth and continuous boundaries, protected edge information from blurring, and was slightly more efficient. When Mickey Mouse depth images were used as experimental subjects, the computational time was reduced by 12.62 seconds; when rabbit depth images were used, computational time was reduced by 17.53 seconds.

Conclusion: Morphological edge operator algorithm proposed in this paper is much more effective than traditional edge detection operators algorithms for deep image segmentation; it can clearly divide Mickey Mouse's ears, eyes, pupils, nose, and mouth.

Keywords: Morphological edge operator, depth image, edge extraction, image segmentation, skeletonizing, CNN.

Graphical Abstract

[1]
D.R. Abu Avi, "Enhanced fuzzy-based local information algorithm for sonar image segmentation", IEEE Trans. Image Process., vol. 29, pp. 445-460, 2019.
[http://dx.doi.org/10.1109/TIP.2019.2930148]
[2]
A. Mahnoor, G.S. Omer, and W. Asim, "Brain tumour image segmentation using EEP networks", IEEE Access, vol. 8, pp. 153589-153598, 2020.
[http://dx.doi.org/10.1109/ACCESS.2020.3018160]
[3]
U.A. Bhatti, Z. Ming-Quan, H. Qing-Song, S. Ali, A. Hussain, Y. Yuhuan, Z. Yu, L. Yuan, and S.A. Nawaz, "Advanced color edge detection using clifford algebra in satellite images", IEEE Photonics J., vol. 13, no. 2, pp. 1-20, 2021.
[http://dx.doi.org/10.1109/JPHOT.2021.3059703]
[4]
X. Cai, X. Li, N. Razmjooy, and N. Ghadimi, "Breast cancer diagnosis by convolutional neural network and advanced thermal exchange optimization algorithm", Comput. Math. Methods Med., vol. 2021, p. 5595180, 2021.
[http://dx.doi.org/10.1155/2021/5595180] [PMID: 34790252]
[5]
C.A. Jing-kang, "Space plant image segmentation based on deep features fusion", Comput. Modernization, vol. 26, no. 10, pp. 58-62, 2018.
[6]
C. Hao-Tian, Z. Yang, and Z. Yu-tong, "Indoor red green blue-depth segmentation based on object-object supportive semantic relationships", Contr. Theory Appl., vol. 36, no. 4, pp. 579-588, 2019.
[7]
L. Chen, "Novel range image segmentation using region-growing and surface classification", Chin. J. Mech. Eng., vol. 40, no. 2, pp. 161-170, 2019.
[http://dx.doi.org/10.3901/JME.2004.02.161]
[8]
C. Di, "Image segmentation algorithm based on partial differential equation", J. Intell. Fuzzy Syst., vol. 40, no. 4, pp. 5945-5952, 2021.
[http://dx.doi.org/10.3233/JIFS-189434]
[9]
Z. Guo, L. Xu, and S. Yujuan, "Novel computer aided lung cancer detection based on convolutional neural network based and feature-based classifiers using metaheuristics", Int. J. Imaging Syst. Technol., vol. 31, no. 4, pp. 1954-1969, 2021.
[http://dx.doi.org/10.1002/ima.22608]
[10]
Y. Han, and Z. Zheng, "Deep learning assisted image interactive framework for brain image segmentation", IEEE Access, vol. 8, pp. 117028-117035, 2020.
[http://dx.doi.org/10.1109/ACCESS.2020.3003624]
[11]
H. An, and R. Navid, "Brain tumor diagnosis based on metaheuristics and deep learning", Int. J. Imaging Syst. Technol., vol. 31, no. 2, pp. 657-669, 2021.
[http://dx.doi.org/10.1002/ima.22495]
[12]
L. Jian, K.Y. Liu, and X.S. Ren, "Application of canny algorithm based on adaptive threshold in MR Image edge detection", J. Jilin Univ., vol. 51, no. 2, pp. 712-719, 2021.
[http://dx.doi.org/10.13229/j.cnki.jdxbgxb20200839]
[13]
L.I.U. Hui, S.H.I. Xiao-long, and Q.I. Kun-yuan, "Automatic image segmentation combined grabcut and depth information", J. Chin. Comput. Syst., vol. 39, no. 10, pp. 2309-2313, 2018.
[14]
T. Liang, Key Technology Research of Augmented Reality Based on Deep Learning., Hebei Normal University, 2019.
[15]
Q. Tian, W. Yongtang, and X. Ren, "“A new optimized sequential method for lung tumor diagnosis based on deep learning and converged search and rescue algorithm”, Biomed", Signal Process Contr., vol. 68, p. 102761, 2021.
[http://dx.doi.org/10.1016/j.bspc.2021.102761]
[16]
T. Zhi-guo, O.U. Jian-ping, and Z. Jun, "Multi-feature combined depth image segmentation algorithm", Comput. Eng. Sci., vol. 40, no. 8, pp. 1429-1434, 2018.
[http://dx.doi.org/10.1007/s11036-019-01454-w]
[17]
G. Wang, J. Meng, and Z. Li, "Adaptive extraction and refinement of marine lanes from crowdsourced trajectory data", Mob. Netw. Appl., vol. 25, no. 4, pp. 1392-1404, 2020.
[18]
W. Ting, Research on three - dimensional measurement technology based on binary defocusing structured light., Zhejiang University, 2020.
[19]
Y. Wen, H.E. Hongzhou, and L.I. Haiyang, "An improved edge detection algorithm for Roberts and gray relational analysis", J. Graph., vol. 35, no. 4, pp. 638-641, 2014.
[20]
W. Xuan, W.A.N.G. Yan, and C.H.E.N. Xing, "Fast image segmentation model without initial contour", Comput. Eng. Appl., vol. 55, no. 11, pp. 167-171, 2019.
[21]
Y. He, Q. Zhao, and X. Min, "Edge detection and repair of PCBA components based on adaptive canny operator", Guangxue Xuebao, vol. 41, no. 5, p. 0515003, 2021.
[http://dx.doi.org/10.3788/AOS202141.0515003]
[22]
X. Yu, Z. Wang, and Y. Wang, "Edge detection of agricultural products based on morphologically improved canny algorithm", Math. Probl. Eng., vol. 2021, no. 3, pp. 1-10, 2021.
[http://dx.doi.org/10.1155/2021/6664970]
[23]
Z. Mei, J. Wen, and X. Peng, "Segmentation for range image based on snake active contour model", Int. J. Signal Process. Image Process Pattern Recognit., vol. 9, no. 8, pp. 393-400, 2016.
[http://dx.doi.org/10.14257/ijsip.2016.9.8.33]
[24]
Z. Mei, W. Jing-hua, Z. Zuxun, and Z. Jianqing, "Comparison of differential and morphological depth image segmentation", Comput. Eng Appl., vol. 46, no. 19, pp. 173-181, 2010.
[25]
Z. Mei, J. Wen, Z. Zhang, and J. Zhang, "Image segmentation based on morphological waterline area", Opt. Technol., vol. 35, no. 3, pp. 326-329, 2009.
[26]
Z. Mei, and Z. Zhang, "Study of depth map segmentation based on differential invariant and region growing method", Comput. Eng., vol. 34, no. 19, pp. 15-17, 2008.