Structuring the search space based on domain-specific vocabulary (or concepts) is capital for enhanced image retrieval. In this paper, we study the opportunities and the impact of exploiting such a strategy in a particular problem which is the leaf species identification. We believe that such a solution is promising to reduce the effect of the high variability across and within species and define more specific and relevant leaf image representations. Among botanical concepts that describe leaves (and particularly their architecture), we focus mainly on three of the most basic and commonly-used concepts: the leaf arrangement, lobation and partition. These concepts define two different structuring types:(1) One is a coarse categorisation of leaf datasets into three subsets, namely simple lobed, simple not lobed and compound (2) The other is a decomposition of the entire leaf images into semantic regions (or parts). We perform the whole structuring process automatically by defining simple geometric parameters (extracted from the leaf contour) based on the analysis of botanical definitions. A fine recognition process is then established in order to determine the species identity. It is defined, typically, using standard (texture or contour) descriptors followed by a KNN classifier. Enriched by the proposed structuring process, the search for species candidates will be restricted to the correspondent category of the query and based on a fusion of each part responses. Experiments carried out on the Scan Pictures of the ImageCLEF 2011 dataset (3070 images totalling 70 species) have shown an increase in performances for different descriptor configurations compared to global leaf representations as well as to some recent related studies.