We propose a novel scene categorization method based on multiscale category-specific visual words. The novelty of the proposed method lies in two aspects: (1) visual words are quantized in a multiscale manner that combines the global-feature-based and local-feature-based scene categorization approaches into a uniform framework; (2) unlike traditional visual word creation methods, which quantize visual words from the entire set of training, we form visual words from the training images grouped in different categories and then collate visual words from different categories to form the final codebook. This generation strategy is capable of enhancing the discriminative ability of the visual words, which is useful for achieving better classification performance. The proposed method is evaluated over two scene classification data sets with 8 and 13 scene categories, respectively. The experimental results show that the classification performance is significantly improved by using the multiscale category-specific visual words over that achieved by using the traditional visual words. Moreover, the proposed method is comparable with the best methods reported in previous literature in terms of classification accuracy rate (88.81% and 85.05% accuracy rates for data sets 1 and 2, respectively) and has the advantage in simplicity.