Prof. Ahmed Abdel Sattar Shaker :: Publications:

Combining multiple classifiers is one of the most important topics in pattern recognition. In this paper the idea is to combine classifiers with different error types based on Fuzzy Majority Voting (FMV). Four study areas with different sensors and scene characteristics were used to assess the performance of the model. First, the lidar point clouds were filtered to generate a Digital Terrain Model (DTM), and then a Digital Surface Model (DSM) and the Normalized Digital Surface Model (nDSM) were generated. A total of 25 uncorrelated feature attributes have been generated from the aerial images, the lidar intensity image, DSM and nDSM. Three different classification algorithms were used to classify buildings, trees, roads and ground from aerial images, lidar data and the generated attributes. The used classifiers include: Self-Organizing Map (SOM); Classification Trees (CTs); and Support Vector Machines (SVMs) with average classification accuracies of 96.8%, 95.9% and 93.7% obtained for SVMs, SOM, and CTs respectively. FMV, which is a powerful tool for combining classifiers, was then applied for combining the class memberships from the three classifiers. The main aim is to reduce overlapping regions of different classes for minimizing misclassification errors. The outcomes demonstrate that use of FMV based combination is essential to achieve the significant improvement in the classification accuracies. The average commission and omission errors has been reduced by about 76.25% and 63.34% respectively compared to the best single classifier