Hyperspectral image compression employing a model of anomalous pixels

Abstract—We propose a new lossy compression algorithm for hyperspectral images, which is based on the spectral Karhunen– Loève transform, followed by spatial JPEG 2000, which employs a model of anomalous pixels during the compression process. Results on Airborne Visible/Infrared Imaging Spectrometer scenes show that the new algorithm provides better rate-distortion performance, as well as improved anomaly detection performance, with respect to the state of the art. Index Terms—Anomaly detection, discrete wavelet transform (DWT), hyperspectral data, JPEG 2000, Karhunen–Loève transform (KLT), lossy compression, Reed–Xiaoli (RX) algorithm, wavelet. I