Combining data from different sensors has the potential to result in more accurate classification than a single sensor. The availability of high quality RGB and LIDAR data provides efficient image classification using the complementary properties of these data sources. This work mainly integrates Genetic Algorithms (GAs) with different fitness functions to extract buildings, trees, roads and grass from aerial images and LIDAR data. K-Means (KM) and Fuzzy C-means (FCM) algorithms were tested and compared, as fitness functions for GAs. Three groups of data were applied which include: RGB group; RGB/LIDAR data group and RGB/LIDAR/attributes group. Error matrix and K-HAT (kappa) statistics were adopted as well as visual inspection to evaluate the validity and robustness of the proposed techniques. FCM proved to be a preferable fitness function for GAs-based classification from aerial images and LIDAR data with accurate average classifications of 87.84%.