This paper presents a methodology for characterizing the behaviour of wavelet-based image coding systems in the presence of faults. This is a previous step in the development of efficient concurrent error detection techniques for such systems. The faulty behaviour of complex signal processing systems is better described at the algorithmic level (i.e., checking the accomplishment of a given functional property by large blocks of data) rather than using the "classical" approach at the structural (i.e., building block) level. Therefore, the issues related to algorithmic fault detection are addressed. Two different platforms for error characterization are presented and their main characteristics are discussed. Experimental results are presented that prove the suitability of the proposed methodology for the target application.