Text
The method of ablation imprints is widely used for spatial characterization of focused X-ray laser beams. However, the analysis of ablation imprints data represents a laborious task for human analysts. The method presented in this Paper employs a deep convolutional neural network U-Net to annotate ablation threshold contours in microscopy image data. Furthermore, postprocessing
procedures are developed to enable automated evaluation of laser beam characteristics.
Description
Schematic of the U-Net architecture with an input image size N=1024, lU=4 descent levels, eU=2 encoding layers per level, and kU=16 convolution kernels in the first level. Light blue and gray boxes represent three-dimensional matrices (multi-channel feature maps) with dimensions indicated on the left and above the box. The left and right part of the image depicts the encoder (contracting path) and decoder (expansive path), respectively. Convolutions with learnable 3x3 kernels combined with the ReLU operation are indicated by blue arrows. Red downward arrows depict the max-pooling operation halving the image resolution. Green upward arrows represent 2x2 up-convolutions (upsampling) doubling the image resolution. In each descent level, skip connections (grey arrows) transfer information from encoder to decoder to better localize fine features.
Contact person: Jaromír Chalupský