Data-driven Feature Sampling for Deep Hyperspectral Classification and Segmentation

TL;DR

This paper introduces a data-driven feature sampling method for hyperspectral image classification and segmentation, significantly reducing input features while maintaining high accuracy using deep learning techniques.

Contribution

It presents an iterative feature selection approach guided by classification accuracy, enabling deep networks to operate with 90% fewer features in hyperspectral data.

Findings

Achieved successful cell classification and segmentation.

Reduced input features by 90% with minimal accuracy loss.

Demonstrated effectiveness on a cyanobacteria dataset.

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 $\textit{Synechocystis sp.}$ 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.