Cascading classifiers for consumer image indexing

We propose a cascading framework of binary classifiers to extract and combine intra-image and inter-class semantics for image indexing and retrieval. Support vector detectors are first trained on semantic support regions without image segmentation. The reconciled and aggregated detection-based indexes then serve as input for support vector learning of image classifiers to generate class-relative image indexes. During retrieval, similarities based on both indexes are combined to rank images. Query by-example experiments on 2400 heterogeneous consumer photos with 16 semantic queries show that the combined matching approach is better than matching with single index. It also outperformed combined matching of color and texture features by 55% in average precision.