In this study, an approach for pixel unmixing based on possibilistic similarity is proposed. This approach, due to the use of possibilistic concepts, enables an important flexibility to integrate both contextual information and a priori knowledge. Possibility distributions are, first, obtained using a priori knowledge given in the form of learning areas delimitated by an expert. These areas serve for the estimation of the probability density functions of different thematic classes. The resulting probability density functions are then transformed into possibility distributions using Dubois-Prade's probability-possibility transformation. Several possibilistic similarity measures were tested in order to improve the discrimination between classes. The pixel unmixing is then performed based on the possibilistic similarity between a local possibility distribution estimated around the considered pixel and the obtained possibility distributions representing the predefined thematic classes in the analyzed image. Accuracy analysis of pixels unmixing demonstrates that the proposed approach represents an efficient estimator of their abundances of the predefined thematic classes and, in turn, higher classification accuracy is achived. Synthetic images are used in order to evaluate the performances of the proposed approach.