Pre-processing and classification of hyperspectral imagery via selective inpainting

Victoria Chayes, Kevin Miller, Rasika Bhalerao, Jiajie Luo, Wei Zhu, Andrea Bertozzi, Wenzhi Liao, Stanley Osher

Research output: Contribution to conferencePaper

1 Citation (Scopus)

Abstract

We propose a semi-supervised algorithm for processing and classification of hyperspectral imagery. For initialization, we keep 20% of the data intact, and use Principal Component Analysis to discard voxels from noisier bands and pixels. Then, we use either an Accelerated Proximal Gradient algorithm (APGL), or a modified APGL algorithm with a penalty term for distance between inpainted pixels and endmembers (APGL Hyp), on the initialized datacube to inpaint the missing data. APGL and APGL Hyp are distinguished by performance on datasets with full pixels removed or extreme noise. This inpainting technique results in band-by-band datacube sharpening and removal of noise from individual spectral signatures. We can also classify the inpainted cube by assigning each pixel to its nearest endmember via Euclidean distance. We demonstrate improved accuracy in classification over data-mining techniques like k-means, unmixing techniques like Hierarchical Non-Negative Matrix Factorization, and graph-based methods like Non-Local Total Variation.
Original languageEnglish
Pages6195-6199
Number of pages5
DOIs
Publication statusPublished - 19 Jun 2017
Event2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) - New Orleans, United States
Duration: 5 Mar 20179 Mar 2017

Conference

Conference2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Abbreviated titleICASSP 2017
CountryUnited States
CityNew Orleans
Period5/03/179/03/17

Keywords

  • hyperspectral imagery (HSI)
  • data preprocessing
  • image inpainting
  • image classification
  • image enhancement

Cite this

Chayes, V., Miller, K., Bhalerao, R., Luo, J., Zhu, W., Bertozzi, A., Liao, W., & Osher, S. (2017). Pre-processing and classification of hyperspectral imagery via selective inpainting. 6195-6199. Paper presented at 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), New Orleans, United States. https://doi.org/10.1109/ICASSP.2017.7953347