Correlation-based inter and intra-band predictions for lossless compression of multispectral images

We present a new lossless compressor for multispectral images having few bands. The mentioned compressor takes into account variations in spectral correlation in order to determine the appropriate spectral and spatial prediction to be performed. The algorithm exploits 2 different facts. On one hand, highly correlated bands may be efficiently compressed with fast computations. On the other hand, a class–conditioned wavelet–based compressor, which is more time-consuming, has given very high compression ratios, even in the case of lowly correlated bands. Our correlationdependent hybrid algorithm yields high compression ratios, outperforming state-of-the-art lossless compressors, and has reasonable execution times. Keywords— prediction, wavelet coefficients, classification, multispectral, lossless compression.