Journal of Information Processing Systems

Korea Information Processing Society (한국정보처리학회)
권호 표지
DOI QR코드

DOI QR Code

A Deep Learning-Based Image Semantic Segmentation Algorithm

  • Received : 2022.03.10
  • Accepted : 2022.08.04
  • Published : 2023.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

This paper is an attempt to design segmentation method based on fully convolutional networks (FCN) and attention mechanism. The first five layers of the Visual Geometry Group (VGG) 16 network serve as the coding part in the semantic segmentation network structure with the convolutional layer used to replace pooling to reduce loss of image feature extraction information. The up-sampling and deconvolution unit of the FCN is then used as the decoding part in the semantic segmentation network. In the deconvolution process, the skip structure is used to fuse different levels of information and the attention mechanism is incorporated to reduce accuracy loss. Finally, the segmentation results are obtained through pixel layer classification. The results show that our method outperforms the comparison methods in mean pixel accuracy (MPA) and mean intersection over union (MIOU).

Keywords

Acknowledgement

This work is supported by 2019 training plan for young backbone teachers in Henan Higher Vocational School (No. 2019GZGG100).

References

  1. L. C. Chen, G. Papandreou, I. Kokkinos, K. Murphy, and A. L. Yuille, "Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 40, no. 4, pp. 834-848, 2018. https://doi.org/10.1109/TPAMI.2017.2699184
  2. H. Yu, Z. Yang, L. Tan, Y. Wang, W. Sun, M. Sun, and Y. Tang, "Methods and datasets on semantic segmentation: a review," Neurocomputing, vol. 304, pp. 82-103, 2018. https://doi.org/10.1016/j.neucom.2018.03.037
  3. S. Cui, C. Liu, M. Chen, and S. Xiong, "Brain tumor semantic segmentation from MRI image using deep generative adversarial segmentation network," Journal of Medical Imaging and Health Informatics, vol. 9, no. 9, pp. 1913-1919, 2019. https://doi.org/10.1166/jmihi.2019.2814
  4. M. Shahzad, A. I. Umar, M. A. Khan, S. H. Shirazi, Z. Khan, and W. Yousaf, "Robust method for semantic segmentation of whole-slide blood cell microscopic images," Computational and Mathematical Methods in Medicine, vol. 2020, article no. 4015323, 2020. https://doi.org/10.1155/2020/4015323
  5. S. Ghosh, A. Pal, S. Jaiswal, K. C. Santosh, N. Das, and M. Nasipuri, "SegFast-V2: semantic image segmentation with less parameters in deep learning for autonomous driving," International Journal of Machine Learning and Cybernetics, vol. 10, pp. 3145-3154, 2019. https://doi.org/10.1007/s13042-019-01005-5
  6. Q. Ning, J. Zhu, and C. Chen, "Very fast semantic image segmentation using hierarchical dilation and feature refining," Cognitive Computation, vol. 10, pp. 62-72, 2018. https://doi.org/10.1007/s12559-017-9530-0
  7. Z. Lu and D. Chen, "Weakly supervised and semi-supervised semantic segmentation for optic disc of fundus image," Symmetry, vol. 12, no. 1, article no. 145, 2020. https://doi.org/10.3390/sym12010145
  8. A. Ion, J. Carreira, and C. Sminchisescu, "Probabilistic joint image segmentation and labeling by figure-ground composition," International Journal of Computer Vision, vol. 107, pp. 40-57, 2014. https://doi.org/10.1007/s11263-013-0663-7
  9. E. Akbas and N. Ahuja, "Low-level hierarchical multiscale segmentation statistics of natural images," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 36, no. 9, pp. 1900-1906, 2014. https://doi.org/10.1109/TPAMI.2014.2299809
  10. C. Menart, J. W. Davis, M. N. Akbar, and R. Ilin, "Scene-based priors for bayesian semantic image segmentation," International Journal of Smart Security Technologies (IJSST), vol. 6, no. 1, pp. 1-14, 2019. https://doi.org/10.4018/IJSST.2019010101
  11. D. Di Mauro, A. Furnari, G. Patane, S. Battiato, and G. M. Farinella, "Estimating the occupancy status of parking areas by counting cars and non-empty stalls," Journal of Visual Communication and Image Representation, vol. 62, pp. 234-244, 2019. https://doi.org/10.1016/j.jvcir.2019.05.015
  12. J. Xie, L. Yu, L. Zhu, and X. Chen, "Semantic image segmentation method with multiple adjacency trees and multiscale features," Cognitive Computation, vol. 9, no. 2, pp. 168-179, 2017. https://doi.org/10.1007/s12559-016-9441-5
  13. X. Xia, Q. Lu, and X. Gu, "Exploring an easy way for imbalanced data sets in semantic image segmentation," Journal of Physics: Conference Series, vol. 1213, no. 2, article no. 022003, 2019. https://doi.org/10.1088/1742-6596/1213/2/022003
  14. J. Long, E. Shelhamer, and T. Darrell, "Fully convolutional networks for semantic segmentation," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, no. 4, pp. 640-651, 2017. https://doi.org/10.1109/TPAMI.2016.2572683
  15. H. Zhao, J. Shi, X. Qi, X. Wang, and J. Jia, "Pyramid scene parsing network," 2016 [Online]. Available from: https://arxiv.org/abs/1612.01105.
  16. Y. Lu, Y. Chen, D. Zhao, and J. Chen, "Graph-FCN for image semantic segmentation," in Advances in Neural Networks - ISNN 2019. Cham, Switzerland: Springer, 2019, pp. 97-105.
  17. Y. Wang, J. Han, J. Lu, L. Bai, and Z. Zhao, "TIG stainless steel molten pool contour detection and weld width prediction based on Res-Seg," Metals, vol. 10, no. 11, article no. 1495, 2020. https://doi.org/10.3390/met10111495
  18. L. H. Li, B. Qian, J. Lian, W. N. Zheng, and Y. F. Zhou, "Study on semantic image segmentation based on convolutional neural network. Journal of Intelligent & Fuzzy Systems, vol. 33, no. 6, pp. 3397-3404, 2017. https://doi.org/10.3233/JIFS-162254
  19. W. Wang, Y. Fu, F. Dong, and F. Li, "Semantic segmentation of remote sensing ship image via a convolutional neural networks model," IET Image Processing, vol. 13, no. 6, pp. 1016-1022, 2019. https://doi.org/10.1049/iet-ipr.2018.5914
  20. V. Romanuke, "A generator of a toy dataset of multi-polygon monochrome images for rapidly testing and prototyping semantic image segmentation networks," The Scientific Journal of Riga Technical University-Electrical, Control and Communication Engineering, vol. 15, no. 2, pp. 54-61, 2019. https://doi.org/10.2478/ecce-2019-0008
  21. R. Jayadevan and V. S. Sheeba, "A semantic image retrieval technique through concept co-occurrence based database organization and DeepLab segmentation," Journal of Computer Science, vol. 16, no. 1, pp. 56-71, 2020. https://doi.org/10.3844/jcssp.2020.56.71
  22. H. Zhou, A. Han, H. Yang, and J. Zhang, "Edge gradient feature and long distance dependency for image semantic segmentation," IET Computer Vision, vol. 13, no. 1, pp. 53-60, 2019. https://doi.org/10.1049/iet-cvi.2018.5035
  23. F. Jiang, A. Grigorev, S. Rho, Z. Tian, Y. Fu, W. Jifara, K. Adil, and S. Liu, "Medical image semantic segmentation based on deep learning," Neural Computing and Applications, vol. 29, pp. 1257-1265, 2018. https://doi.org/10.1007/s00521-017-3158-6