Suscripción a Biblioteca: Guest
Portal Digitalde Biblioteca Digital eLibros Revistas Referencias y Libros de Ponencias Colecciones
Journal of Flow Visualization and Image Processing
SJR: 0.161 SNIP: 0.312 CiteScore™: 0.1

ISSN Imprimir: 1065-3090
ISSN En Línea: 1940-4336

Journal of Flow Visualization and Image Processing

DOI: 10.1615/JFlowVisImageProc.2019030652
pages 239-252

A DEEP LEARNING ALGORITHM FOR PARTICLE SEGMENTATION OF AEROSOL IMAGES

Dong Xiang
School of Computer Science and Technology, Wuhan University of Technology, Wuhan, 430063, China
Di Cai
School of Computer Science and Technology, Wuhan University of Technology, Wuhan, 430063, China
Xiangneng Hu
School of Computer Science and Technology, Wuhan University of Technology, Wuhan, 430063, China
Hanbing Yao
School of Computer Science and Technology, Wuhan University of Technology, Wuhan, 430063, China
Ting Liu
School of Environmental Science & Engineering, Hubei Polytechnic University, Hubei Key Laboratory of Mine Environmental Pollution Control and Remediation, Huangshi, 435003, China
Lung-Wen Antony Chen
Department of Environmental and Occupational Health, School of Community Health Sciences, University of Nevada Las Vegas, Las Vegas, NV, 89154, USA
Mi Zhang
Department of Environmental and Occupational Health, School of Community Health Sciences, University of Nevada Las Vegas, Las Vegas, NV, 89154, USA

SINOPSIS

This paper addresses the task of particle segmentation in high-resolution aerosol images. A particle-boundary model is introduced to predict particles and their boundaries, simultaneously using a fully convolutional neural network. Given a RGB color image, the model directly outputs a predicted particle map and a boundary map. A simple and parameter-free watershed post-processing procedure is performed on the predicted particle and boundary map to produce the final segmented particles. An overlapping 256 × 256 patch extraction method is also designed for seamless prediction of the particle in large images. During the training phase, a combined loss function is used to alleviate the problem of unbalanced classes. We compare two weight initialization schemes: He's normal initializer and one pretrained on the 2018 Data Science Bowl. Experimental results show that the pretrained network is able to converge much faster to its steady value in comparison with the nonpretrained network and achieve higher intersection over union scores. Our method also outperforms the traditional Otsu and triangle methods and gets better segmentation results on raw and contrast adjusted test images.

REFERENCIAS

  1. Alom, M.Z., Hasan, M., Yakopcic, C., Taha, T.M., and Asari, V.K., Recurrent Residual Convolutional Neural Network based on U-Net (r2u-net) for Medical Image Segmentation, Cornell University, from https://arxiv.org/abs/1802.06955, 2018.

  2. Beucher, S. and Lantuej, C., Use of Watersheds in Contour Detection, Proc. of Int. Workshop on Image Processing, Real-Time Edge and Motion Detection/Estimation, Rennes, France, 1979.

  3. Carpenter, A.E., Jones, T.R., Lamprecht, M.R., Clarke, C., Kang, I.H., Friman, O., Guertin, D.A., Chang, J.H., Lindquist, R.A., Moffat, J., Golland, P., and Sabatini, D.M., Cell Profiler: Image Analysis Software for Identifying and Quantifying Cell Phenotypes, Genome Biol., vol. 7, 2006. DOI: 10.1186/ gb-2006-7-10-r100.

  4. Chang, H., Han, J., Borowsky, A., Loss, L., Gray, J.W., Spellman, P.T., and Parvin, B., Invariant Delineation of Nuclear Architecture in Glioblastoma Multiform for Clinical and Molecular Association, IEEE Trans. on Medical Imaging, vol. 32, no. 4, pp. 670-682, 2013.

  5. Chen, L.C., Papandreou, G., Schroff, F., and Adam, H., Rethinking Atrous Convolution for Semantic Image Segmentation, Cornell University, from https://arxiv.org/abs/1706.05587, 2017.

  6. Clevert, D., Thomas, U., and Sepp, H., Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs), Cornell University, from https://arxiv.org/abs/1511.07289, 2015.

  7. Drozdzal, M., Vorontsov, E., Chartrand, G., Kadoury, S., and Pal, C., The Importance of Skip Connections in Biomedical Image Segmentation, Cornell Univerisity, from https://arxiv.org/abs/1608.04117v2, 2016.

  8. Grady, L., Random Walks for Image Segmentation, IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 8, no. 11, pp. 1768-1783, 2006.

  9. He, K., Zhang, X., Ren, S., and Sun, J., Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification, Cornell University from https://arxiv.org/abs/1502.01852, 2015.

  10. Ibtehaz, N. and Rahman, M.S., MultiResUNet: Rethinking the U-Net Architecture for Multimodal Biomedical Image Segmentation, Cornell University from https://arxiv.org/abs/1902.04049, 2019.

  11. Iglovikov, V. and Shvets, A., TernausNet: U-Net with VGG11 Encoder PreTrained on ImageNet for Image Segmentation, Cornell University from https://arxiv.org/abs/1801.05746, 2018.

  12. Jegou, S., Drozdzal, M., Vazquez, D., Romero, A., and Bengio, Y., The One Hundred Layers Tiramisu: Fully Convolutional Dense Nets for Semantic Segmentation, Cornell University, from https://arxiv. org/abs/1611.09326, 2016.

  13. Kingma, D. and Ba, J., Adam: A Method for Stochastic Optimization, Cornell University, from https://arxiv.org/abs/1412.6980, 2014.

  14. Kong, H., Gurcan, M., and Belkacem-Boussaid, K., Partitioning Histopathological Images: An Integrated Framework for Supervised Color Texture Segmentation and Cell Splitting, IEEE Trans. on Medical Imaging, vol. 30, no. 9, pp. 1661-1677, 2011.

  15. Liu, T., Chen, L.-W.A., Zhang, M., Watson, J.G., Chow, J.C., Cao, J.J., Chen, H.Y., Wang, W., Zhang, J.Q., Zhan, C.L., Liu, H.X., Zheng, J.R., Chen, N.W., Yao, R.Z., and Xiao, W.S., Bioaerosol Concentrations and Size Distributions during the Autumn and Winter Seasons in an Industrial City of Central China, Aerosol and Air Quality Res., pp. 1095-1104, 2019.

  16. Long, J., Shelhamer, E., and Darrell, T., Fully Convolutional Networks for Semantic Segmentation, CVPR 2015, Proc. of 2015 IEEE Conf. on Computer Vision and Pattern Recognition, Boston, MA, pp. 3431-3440, 2015.

  17. Maki, T., Hara, K., Iwata, A., Lee, K., Kawai, K., Kai, K., Kobayashi, F., Pointing, S., Archer, S., Hasegawa, H., and Iwasaka, Y., Variations in Airborne Bacterial Communities at High Altitudes over the Noto Peninsula (Japan) in Response to Asian Dust Events, Atmos. Chem. Phys., vol. 17, pp. 11877-11897, 2017.

  18. Oktay, O., Schlemper, J., Folgoc, L.L., Lee, M., Heinrich, M., Misawa, K., Mori, K., McDonagh, S., Hammerla, N.Y., Kainz, B., Glocker, B., and Rueckert, D., Attention U-Net: Learning Where to Look for the Pancreas, Cornell University, from https://arxiv.org/abs/1804.03999, 2018.

  19. Otsu, N., A Threshold Selection Method from Gray-Level Histograms, IEEE Trans. on Systems, Man, and Cybernetics, vol. 9, no. 1, pp. 62-66, 1979.

  20. Ronneberger, O., Fischer, P., and Brox, T., U-Net: Convolutional Networks for Biomedical Image Segmentation, MICCAI 2015, Proc. of 18th Int. Conf. on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany, pp. 234-241, 2015.

  21. Rueden, C.T., Schindelin, J., Hiner, M.C., DeZonia, B.E., Walter, A.E., Arena, E.T., and Eliceiri, K.W., ImageJ2: ImageJ for the Next Generation of Scientific Image Data, BMC Bioinformatics, vol. 18, no. 1, 2017. DOI: 10.1186/s12859-017-1934-z.

  22. Shotton, J., Fitzgibbon, A., Cook, M., Sharp, T., and Finocchio, M., Real-Time Human Pose Recognition in Parts from Single Depth Images, CVPR 2011, Proc. of the 2011 IEEE Conf. on Computer Vision and Pattern Recognition, Colorado Springs, CO, pp. 1297-1304, 2011.

  23. Shotton, J., Johnson, M., and Cipolla, R., Semantic Texton Forests for Image Categorization and Segmentation, CVPR 2008, Proc. of 2008 IEEE Conf. on Computer Vision and Pattern Recognition, Anchorage, Alaska, pp. 1-8, 2008.

  24. Xing, F., Xie, Y., and Yang, L., An Automatic Learning based Framework for Robust Nucleus Segmentation, IEEE Trans. on Medical Imaging, vol. 35, no. 2, pp. 550-566, 2016.

  25. Zack, G.W., Rogers, W.E., and Latt, S.A., Automatic Measurement of Sister Chromatid Exchange Frequency, J. Histochem. Cytochem., vol. 25, no. 7, pp. 741-753, 1977.

  26. Zhou, Z.W., Siddiquee, M.M.R., Tajbakhsh, N., and Liang, J., UNet++: A Nested U-Net Architecture for Medical Image Segmentation, Cornell University, from https://arxiv.org/abs/1807.10165, 2018.

  27. Zuiderveld, K., Contrast Limited Adaptive Histogram Equalization, Graphic Gems IV, San Diego: Academic Press Professional, pp. 474-485, 1994.


Articles with similar content:

Energy-Based Fusion Scheme for Surveillance and Navigation
International Journal for Multiscale Computational Engineering, Vol.8, 2010, issue 6
S. Muttan, K. Mahesh Bharath, S. Senthil Kumar
Color Image Segmentation Based on Fuzzy Rule-Based Reasoning Applied to Colonoscopic Images
Critical Reviews™ in Biomedical Engineering, Vol.28, 2000, issue 3&4
S. M. Krishnan, K. L. Chan, Xin Yang
DROPLET SHADOW VELOCIMETRY BASED ON MONOFRAME TECHNIQUE
Atomization and Sprays, Vol.28, 2018, issue 7
M. J. Akbari, Azadeh Kebriaee, F. Abbasi Zarrin
Algorithm for Determination of the Volume of Steganographic Embedment by the Method of Statistical Analysis of the Histograms of DCT Coefficients of JPEG Format Images
Telecommunications and Radio Engineering, Vol.65, 2006, issue 11-15
V. A. Baranov, O. V. Gatilov
DIGITAL IMAGE ANALYSIS FOR THE INCOHERENT MEDIUM DENSITY PIV
Journal of Flow Visualization and Image Processing, Vol.2, 1995, issue 1
Tomomasa Uemura, Manabu Iguchi, Zen-Ichiro Morita