「海底の地層断面の画像データによる資源探査への機械学習の応用」の説明図
 Original image of a core (top) and the manually edited one, masking the ruler and secondary color artifacts with the alpha channel (bottom) |
 The Fully Convolutional Neural Network (FCN) used for segmentation (from [Long, Shelhamer, Darrell, 2014]) |
 Intersection-over-Union (IoU) is used to compare the performance of the neural net to the manual editing |
|
 Otsu’s binary thresholding method for turning gray scale images into black-and-white ones |
Images of the original core
manually edited
prediction of the FCN