We propose a novel method for the automatic generation of the spatial image filter sequences based on Genetic Programming (GP). In this method, the filter sequences consist of the filters which process Image-Value Pairs. This idea allows the filter sequences to contain not only image processing, but also numerical operations. And we exploit the popular method of the multi-objective optimization to generate the robust filter sequences. We demonstrate the generation of the background elimination filter from the pictures of flowers and also demonstrate the generation of the image classification filters.