NPIC: Hierarchical Synthetic Image Classification Using Image Search and Generic Features
The authors introduce NPIC, an image classification system that focuses on synthetic (e.g., non-photographic) images. They use class-specific keywords in an image search engine to create a noisily labeled training corpus of images for each class. NPIC then extracts both Content-Based Image Retrieval (CBIR) features and metadata-based textual features for each image for machine learning. The authors evaluate this approach on three different granularities: Natural vs. synthetic, map vs. figure vs. icon vs. cartoon vs. artwork and further subclasses of the map and figure classes. The NPIC framework achieves solid performance (99%, 97% and 85% in cross validation, respectively).