http://arxiv.org/abs/1807.01761
We present the Spectral Image Typer (SPIT), a convolutional neural network (CNN) built to classify spectral images. In contrast to traditional, rules-based algorithms which rely on meta data provided with the image (e.g. header cards), SPIT is trained solely on the image data. We have trained SPIT on 2,004 human-classified images taken with the Kast spectrometer at Lick Observatory with types of Bias, Arc, Flat, Science and Standard. We include several pre-processing steps (scaling, trimming) motivated by human practice and also expanded the training set to balance between image type and increase diversity. The algorithm achieved an accuracy of 98.7% on the held-out validation set and an accuracy of 98.7% on the test set of images. We then adopt a slightly modified classification scheme to improve robustness at a modestly reduced cost in accuracy (98.2%). The majority of mis-classifications are Science frames with very faint sources confused with Arc images (e.g. faint emission-line galaxies) or Science frames with very bright sources confused with Standard stars. These are errors that even a well-trained human is prone to make. Future work will increase the training set from Kast, will include additional optical and near-IR instruments, and may expand the CNN architecture complexity. We are now incorporating SPIT in the PYPIT data reduction pipeline (DRP) and are willing to facilitate its inclusion in other DRPs.
V. Jankov and J. Prochaska
Fri, 6 Jul 18
43/52
Comments: Accepted to PASP; 13 pages, 7 figures; See this this https URL for docs
You must be logged in to post a comment.