Buildings are a fundamental component of the built environment, and accurate information regarding their size, location, and distribution is vital for various purposes. The ever-increasing capabilities of unmanned aerial vehicles (UAVs) have sparked an interest in exploring various techniques to delineate buildings from the very high-resolution images obtained from UAV photogrammetry. However, UAV images have limited spectral information, and VIs have been adopted to increase the spectral strength of UAVs for building classification. This study aims to assess the contribution of four VIs, the green leaf index (GLI), red-green-blue vegetation index (RGBVI), visual atmospherically resistant index (VARI), and triangular greenness index (TGI), in improving building classification using geographic object-based image analysis (GeoBIA) approach and random forest classifier. For this purpose, five datasets were created and comprised of the RGB-UAV image and the RGB VIs. The experimental result indicated that the RGB + VARI dataset had the best improvement in the building classification based on four evaluation metrics: overall accuracy (0. 9799), precision (0. 9806), recall (0. 9806), and F1-score (0. 9806). The combination of all the VIs with the RGB image, on the other hand, attained results lower than the standalone RGB image: accuracy (0. 9507), precision (0. 9570), recall (0. 9368), and F1-score (0. 9468).