English

Data-driven Feature Sampling for Deep Hyperspectral Classification and Segmentation

Neural and Evolutionary Computing 2017-10-30 v1 Computer Vision and Pattern Recognition

Abstract

The high dimensionality of hyperspectral imaging forces unique challenges in scope, size and processing requirements. Motivated by the potential for an in-the-field cell sorting detector, we examine a Synechocystis sp.\textit{Synechocystis sp.} PCC 6803 dataset wherein cells are grown alternatively in nitrogen rich or deplete cultures. We use deep learning techniques to both successfully classify cells and generate a mask segmenting the cells/condition from the background. Further, we use the classification accuracy to guide a data-driven, iterative feature selection method, allowing the design neural networks requiring 90% fewer input features with little accuracy degradation.

Keywords

Cite

@article{arxiv.1710.09934,
  title  = {Data-driven Feature Sampling for Deep Hyperspectral Classification and Segmentation},
  author = {William M. Severa and Jerilyn A. Timlin and Suraj Kholwadwala and Conrad D. James and James B. Aimone},
  journal= {arXiv preprint arXiv:1710.09934},
  year   = {2017}
}
R2 v1 2026-06-22T22:27:09.466Z