The method of indexing multimedia documents comprises the following steps: a) for each document identifying and extracting terms t.sub.i constituted by vectors characterizing properties of the; b) storing terms t.sub.i in a term base comprising P terms; c) determining a maximum number N of desired concepts that group together the most pertinent terms t.sub.i; d) calculating the matrix T of distances between the terms t.sub.i of the term base; e) decomposing the set P of terms t.sub.i of the term base into N portions P.sub.j (1.ltoreq.j.ltoreq.N) such that P=P.sub.1.orgate. P.sub.2 . . . .orgate. P.sub.j . . . .orgate. P.sub.N, each portion P.sub.j comprising a set of terms t.sub.ij and being represented by a concept c.sub.j, the terms t.sub.i being distributed in such a manner that the terms that are farther apart are to be found in distinct portions P.sub.l, P.sub.m, and the terms that are closer together are to be found in the same portion P.sub.l; f) structuring the concept dictionary; and g) constructing a fingerprint base made up of the set of concepts c.sub.i representing the terms t.sub.i of the documents, each document being associated with a fingerprint that is specific thereto.