The current study introduces an approach for patternrecognition of drug manufacturers according to theirHPLC trace impurity data. This method considers signalsin phase space and accounts for two different types ofnoise: additive and perturbative. The pharmaceuticalfingerprints are estimated as mean trajectories of HPLCtrace impurity data and are used as reference models forrecognition of new data by the minimal length classifier.The chromatographic trace organic impurity patternscollected from six different manufacturers of l-tryptophanare analyzed as an example. The prediction ability of thenew method tested using three different cross-validationprocedures remains about 95% even if the number ofavailable data in the training sets decreases by 5 times.The accuracy of prediction in phase space is superiorcompared to results calculated using a Window Preprocessing method and artificial neural networks. The difference in performance between new and previous methods becomes more significant under particular conditionsthat are more adequate for practical application of themethod. In addition, the current approach enables simpleand comprehensive interpretation of the calculated results.