The SPectral Image Typer (SPIT)
Viktor Jankov, J. Xavier Prochaska (UC Santa Cruz)

TL;DR
SPIT is a CNN-based tool that classifies spectral images with high accuracy using only image data, outperforming traditional rule-based methods reliant on meta data, and is integrated into data reduction pipelines.
Contribution
This paper introduces SPIT, a CNN trained solely on spectral image data for classification, achieving over 98% accuracy and improving robustness over traditional methods.
Findings
Achieved 98.7% accuracy on validation and test sets.
Effective classification of spectral image types with minimal meta data.
Potential for broad application in spectral data pipelines.
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsGaussian Processes and Bayesian Inference · Time Series Analysis and Forecasting · Machine Learning and Data Classification
