Fig. 2: Computer vision segmentation of hyperspectral data from high-throughput (HT) synthesized semiconductors.
From: Using scalable computer vision to automate high-throughput semiconductor characterization
a Raw hyperspectral datacube, Ω, captured using a hyperspectral imager (Resonon, Pika L) of HT-deposited formamidinium (FA) and methylammonium (MA) mixed-cation perovskites FA1−xMAxPbI3. (X, Y) represents the pixel coordinates, and R(λ) represents the reflectance spectra for each pixel. Each sample is deposited onto the glass substrate with a unique composition 0 ≤ x ≤ 1 and flexible form factor geometry. b Computer-vision segmented datacube, Φ, that pairs each unique sample’s pixels, \({(\widehat{{{{{{{{\bf{X}}}}}}}}},\widehat{{{{{{{{\bf{Y}}}}}}}}})}_{n}\in N\), to its reflectance spectra, R(λ). The gray hatched region indicates the discarded background pixels.
