Abstract
In this paper, we combine superpixel and deep learning models to propose a new unsupervised image segmentation based on region-combined color images. Compared to other region merging algorithms, our algorithm can automatically segment color images without human interaction. The algorithm has three phases. In the first phase, we use the mean shift algorithm to obtain non-overlapping over-segmented regions. Firstly, the image is initially segmented by the superpixel segmentation algorithm, then the saliency map is obtained by the superpixel similarity, and the semi-supervised region is merged into an unsupervised algorithm by the saliency map. Finally, the resulting picture is sent to the deep learning model for training to get the final segmentation picture. A large number of experiments have been carried out, and the results show that the scheme can reliably extract the contour of the object from the complex background.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
M. Buda, A. Maki, M.A. Mazurowski, A systematic study of the class imbalance problem in convolutional neural networks. Neural Netw. 106, 249–259 (2018)
M. Cheng, N.J. Mitra, X. Huang, P.H. Torr, S. Hu, Global contrast based salient region detection. IEEE Trans. Pattern Anal. Mach. Intell. 37(3), 569–582 (2015)
K. Cui, X. Qin, Virtual reality research of the dynamic characteristics of soft soil under metro vibration loads based on BP neural networks. Neural Comput. Appl. 29(5), 1233–1242 (2018)
K. Cui, X. Jing, Research on prediction model of geotechnical parameters based on BP neural network. Neural Comput. Appl. 29(6), 1–11 (2018)
Y. Han, J. Li, X. Yang, W. Liu, Y. Zhang, Dynamic prediction research of silicon content in hot metal driven by big data in blast furnace smelting process under Hadoop cloud platform. Complexity 2018, 1–16 (2018)
A.K. Helmy, G.S. El-Taweel, Image segmentation scheme based on SOM–PCNN in frequency domain. Appl. Soft Comput. 40, 405–415 (2016)
L. Itti, C. Kouch, E. Niebur, A model of saliency-based visual attention for rapid scene analysis. IEEE Trans. Pattern Anal. Mach. Intell. 20, 1254–1259 (1998)
L. Jiang, X. Hu, Q. Xiao, Y. Gu, Q. Li, Fully automated segmentation of whole breast using dynamic programming in dynamic contrast enhanced MR images. Med. Phys. 44(6), 2400–2414 (2017)
B. Khorram, M. Yazdi, A new optimized thresholding method using ant colony algorithm for MR brain image segmentation. J. Digit. Imaging 32(1), 162–174 (2019)
H. Liang, J. Zou, Rock image segmentation of improved semi-supervised SVM–FCM algorithm based on chaos. Circuits Syst. Signal Process. (2019). https://doi.org/10.1007/s00034-019-01088-z
Y. Liu, C. Mu, W. Kou, J. Liu, Modified particle swarm optimization-based multilevel thresholding for image segmentation. Soft Comput. 19(5), 1311–1327 (2015)
M.A. Mohammed, M.K.A. Ghani, R.I. Hamed, M.K. Abdullah, D.A. Ibrahim, Automatic segmentation and automatic seed point selection of nasopharyngeal carcinoma from microscopy images using region growing based approach. J. Comput. Sci. 20, 61–69 (2017)
J. Ning, L. Zhang, D. Zhang, C. Wu, Interactive image segmentation by maximal similarity based region merging. Pattern Recognit. 43(2), 445–456 (2010)
N. Ostu, A threshold selection method from grey-level histograms. Man Cybern. 9(1), 62–66 (2007)
J. Peng, Y. Shao, Intelligent method for identifying driving risk based on V2V multisource big data. Complexity 2018, 1–9 (2018)
U.K. Sharma, K. Kumawat, Review of histogram based image contrast enhancement techniques. Int. J. Res. Eng. Technol. (IJRET) 3(2), 65–76 (2015)
R. Sujee, S. Padmavathi, Image enhancement through pyramid histogram matching, in IEEE 2017 International Conference on Computer Communication and Informatics (ICCCI) (2017), pp. 1–5
Q. Wang, J. Gao, Y. Yuan, A joint convolutional neural networks and context transfer for street scenes labeling. IEEE Trans. Intell. Transp. Syst. 19(5), 1457–1470 (2018)
W. Wei, H. Song, H. Wang, X. Fan, Research and simulation of queue management algorithms in ad hoc networks under DDoS attack. IEEE Access 5, 27810–27817 (2017)
Y. Wu, T. Hassner, K. Kim, G. Medioni, P. Natarajan, Facial landmark detection with tweaked convolutional neural networks. IEEE Trans. Pattern Anal. Mach. Intell. 40(12), 3067–3074 (2018)
Y. Yan, S. Gao, S. Cao, Active contour based natural color images segmentation. J. Comput. Inf. Syst. 8(9), 3707–3714 (2012)
E. Yelmanova, Y. Romanyshyn, Histogram-based method for image contrast enhancement, in Experience of Designing and Application of CAD Systems in Microelectronics (CADSM) (IEEE, 2017), pp. 165–169
S.X. Yu, Segmentation using multiscale cues, in IEEE Computer Society Conference on Computer Vision & Pattern Recognition (2004), pp. 247–254
F. Zhao, H. Liu, J. Fan, A multiobjective spatial fuzzy clustering algorithm for image segmentation. Appl. Soft Comput. 30, 48–57 (2015)
Y. Zheng, B. Jeon, D. Xu, W.Q.M. Jonathan, H. Zhang, Image segmentation by generalized hierarchical fuzzy \(C\)-means algorithm. J. Intell. Fuzzy Syst. 28(2), 961–973 (2015)
H. Zhu, C. Li, L. Zhang, J. Shen, River channel extraction from SAR images by combining gray and morphological features. Circuits Syst. Signal Process. 34(7), 2271–2286 (2015)
Acknowledgements
This research is supported by National Natural Science Foundation of China under Grant No. F020308 and the Key Research and Development Project of Shanxi Province under Grant No. 201803D31055.
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
Mu, X., Qi, H. & Li, X. Automatic Segmentation of Images with Superpixel Similarity Combined with Deep Learning. Circuits Syst Signal Process 39, 884–899 (2020). https://doi.org/10.1007/s00034-019-01249-0
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00034-019-01249-0