Abstract
Objects of interest are rendered from spectral images. Seven types of blood and cancer cells are imaged in a microscope with changes in source illumination and sensor gain over one year calibrated. Chromatic distortion is measured and corrections analyzed. Background is discriminated with binary decisions generated from a training sample pair. A filter is derived from two sample-dependent binary decision parameters: a linear discriminant and a minimum error bias. Excluded middle decisions eliminate order-dependent errors. A global bias maximizes the number and size of spectral objects. Sample size and dimensional limits on accuracy are described using a covariance stability relation.
© 2022 Optica Publishing Group
Full Article | PDF ArticleMore Like This
Valero Laparra, Alexander Berardino, Johannes Ballé, and Eero P. Simoncelli
J. Opt. Soc. Am. A 34(9) 1511-1525 (2017)
Shoji Tominaga, Shogo Nishi, Ryo Ohtera, and Hideaki Sakai
J. Opt. Soc. Am. A 39(3) 494-508 (2022)
Khalil Huraibat, Esther Perales, Eric Kirchner, Ivo Van der Lans, Alejandro Ferrero, and Joaquín Campos
J. Opt. Soc. Am. A 38(3) 328-336 (2021)