We propose to combine support vector machine (SVM) models learned from different visual features for efficiently classifying fingerprint images. Real datasets of fingerprint images are collected from students at the Can Tho University. The SVM algorithm learns classification models from the handcrafted features such as the scale-invariant feature transform (SIFT) and the bag-of-words (BoW) model, the histogram of oriented gradients (HoG), the deep learning of invariant features Xception, extracted from fingerprint images. Followed which, we propose to train a neural network for combining SVM models trained on these different visual features, making improvements of the fingerprint image classification. The empirical test results show that combining SVM models is more accurate than SVM models trained on any single visual feature type. Combining SVM-SIFT-BoW, SVM-HoG, SVM-Xception improves 11.17%, 14.07%, 10.83% classification accuracy of SVM-SIFT-BoW, SVM-HoG and SVM-Xception, respectively.