The wide usage of small satellite imagery, especially its commercialization makes application based on-board compression not only meaningful but also necessary in order to solve the bottleneck between the huge volume of data generated on-board and the very limited downlink bandwidth. In this paper, we propose a method which encodes different regions with different algorithms. We use three shape-adaptive image compression algorithms to be the candidates. The first one is a JPEG-based algorithm; the second one is based on the Object- based Wavelet Transform (OWT) method proposed by Katata; the third adopts Hilbert scanning of the regions of interest followed by one dimensional (1-D) wavelet transform. The three algorithms are also applied to the full image so that we can compare their performance on who rectangular image. We use eight Landsat TM multi-spectral images as our test set. The results show that these compression algorithms have significantly different performance for different regions. For relatively smooth regions, e.g. regions that consist of a single type of vegetation or water areas etc., the 1-D wavelet method is the best; for highly textured regions, e.g. urban areas, mountain areas and so on, the modified OWT method wins over the others; for the whole image, OWT working at whole image mode, which is just an ordinary 2-D wavelet compression, is more suitable. Based on this, we propose a new application based compression architecture which encodes different regions with different algorithms.