In lithological and mineralogical mapping geons are generated by transforming the solid spatial/spectral information of imagery objects into individual rocks and minerals through complex algorithms including interpolation, segmentation, generalization, and regionalization. In geological applications, the foundation of most remote sensing image interpretation is based on mapping and classification. The most common classification techniques are established for multispectral data analysis and are pixel-based. As a consequence, such analysis show disadvantages for classification of the hyperspectral images that contain abundant detailed spatial, spectral, and textural information. The major objective of this research was to extract the mineral and rock geons of HyMap mosaicked imagery scenes from Birjand, eastern Iran. The approach combines object based segmentation and machine learning classification algorithms. The utilized imagery was segmented by FODPSO algorithm that creates higher between-class variances while the output image was classified by Gaussian process (GP) algorithm using 272 and 127 geons as training and testing areas. The key alteration minerals including alunite, jarosite, kaolinite, muscovite, and montmorillonite, and the dominant rock types consisting of granodiorite, tuff breccia, tuff, ignimbrite, dacite, and andesite were mapped accordingly. All of the geons were verified through field observations and the final output map showed an overall accuracy of 89.66 %. This investigation showed that integration of FODPSO and GP algorithms could be introduced as a new approach to create geons of rocks and minerals, and for lithological and mineralogical mapping in various geological settings.