Ore Image Segmentation Method of Conveyor Belt Based on U-Net and Res_UNet Models

被引：4
|
作者：
Liu X.-B. [1 ]
Zhang Y.-W. [1 ]
机构：
[1] Intelligent Mine Research Center, Northeastern University, Shenyang
来源：
Dongbei Daxue Xuebao/Journal of Northeastern University | 2019年 / 40卷 / 11期
关键词：
Conveyor belt; Deep learning; Ore segmentation; Res_UNet; U-Net;
D O I：
10.12068/j.issn.1005-3026.2019.11.019
中图分类号：
学科分类号：
摘要：
Aiming at the problem of inaccurate segmentation caused by the adhesion and edge blurring of the ore image in the conveyor belt, a method for ore image segmentation of conveyor belt based on U-Net and Res_UNet models is proposed. Firstly, the image to be segmented is processed by gray-scale, median filtering and adaptive histogram equalization, and then the pre-trained U-Net model is used to extract the image contour. Then, after binary image contour, the pre-trained Res_UNet model is used for contour optimization. Finally, OpenCV is used to obtain the segmentation result. Compared with watershed algorithm based on morphological reconstruction and NUR method for 10 test images, the proposed method for ore contour detection and optimization based on deep learning is more accurate, proving its effectiveness for image segmentation of conveyor belt ores. © 2019, Editorial Department of Journal of Northeastern University. All right reserved.
引用
收藏
页码：1623 / 1629
页数：6
相关论文
共 13 条
  • [1] Zhang G.Y., Liu G.Z., Zhu H., Segmentation algorithm of complex ore images based on templates transformation and reconstruction, International Journal of Minerals Metallurgy and Materials, 18, 4, pp. 385-389, (2011)
  • [2] Amankwah A., Aldrich C., Automatic ore image segmentation using mean shift and watershed transform, Proceedings of 21st International Conference Radioelektronika, pp. 1-4, (2011)
  • [3] Done K., Jiang D.L., Automated estimation of ore size distributions based on machine vision, Lecture Notes in Electrical Engineering, 238, pp. 1125-1131, (2014)
  • [4] Wang R.X., Zhang W.C., Shao L.Z., Research of ore particle size detection based on image processing, Proceedings of 2017 Chinese Intelligent Systems Conference, pp. 505-514, (2017)
  • [5] Zhang G.Y., Liu G.Z., Zhu H., Et al., Ore image thresholding using bi-neighbourhood Otsu's approach, Electronics Letters, 46, 25, pp. 1666-1668, (2010)
  • [6] Malladi S.R.S.P., Ram S., Rodriguez J.J., Superpixels using morphology for rock image segmentation, 2014 Southwest Symposium on Image Analysis and Interpretation, pp. 145-148, (2014)
  • [7] Yang G.Q., Wang H.G., Xu W.L., Et al., Ore particle image region segmentation based on multilevel strategy, Chinese Journal of Analysis Laboratory, 35, 24, pp. 202-204, (2014)
  • [8] Yuan L., Duan Y.Y., A method of ore image segmentation based on deep learning, Lecture Notes in Computer Science, pp. 508-519, (2018)
  • [9] Ronneberger O., Fischer P., Brox T., U-Net: convolutional networks for biomedical image segmentation, International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 234-241, (2015)
  • [10] Su H.-J., Yu Z.-L., Zhang G.-L., Image processing based on openCV, Science & Technology Information, 12, 8, pp. 18-19, (2014)
12