Extreme Learning Machine (ELM) as a type of generalized single-hidden layer feed-forward networks (SLFNs) has demonstrated its good generalization performance with extreme fast learning speed in many benchmark and real applications. This paper further studies the performance of ELM and its variants in object recognition using two different feature extraction methods. The first method extracts texture features, intensity features from Histogram and features from two types of color space: HSV & RGB. The second method extracts shape features based on Radon transform. The classification performances of ELM and its variants are compared with the performance of Support Vector Machines (SVMs). As verified by simulation results, ELM achieves better testing accuracy with much less training time on majority cases than SVM for both feature extraction methods. Besides, the parameter tuning process for ELM is much easier than SVM as well.