Skip to main content
Journal of Analytical Science and Technology
Fig. 6 | Journal of Analytical Science and Technology

Fig. 6

From: Deep learning image segmentation for the reliable porosity measurement of high-capacity Ni-based oxide cathode secondary particles

Fig. 6

Arrays of a the original BSE images and corresponding ground truth input images prepared for the training and performance test of the CNN-based segmentation model. b The corresponding output image arrays generated by the CNN-based segmentation model combined with the histogram stretching and histogram equalization processes. c The corresponding output image arrays generated using the digital threshold process implemented in Avizo software, which has been used for tomographic volume reconstruction

Back to article page