We propose a new Web image selection method which employs the region-based bag-of-features representation. The contribution of this work is (1) to introduce the region-based bag-of-features representation into an Web image selection task where training data is incomplete, and (2) to prove its effectiveness by experiments with both generative and discriminative machine learning methods. In the experiments, we used a multiple-instance learning SVM and a standard SVM as discriminative methods, and pLSA and LDA mixture models as probabilistic generative methods. Several works on Web image filtering task with bag-of-features have been proposed so far. However, in case that the training data includes much noise, sufficient results could not be obtained. In this paper, we divide images into regions and classify each region instead of classifying whole images. By this region-based classification, we can separate foreground regions from background regions and achieve more effective image training from incomplete training data. By the experiments, we show that the results by the proposed methods outperformed the results by the whole-image-based bag-of-features.