Matrix factorization-based clustering of image features for bandwidth-constrained information retrieval

We consider the problem of accurately and efficiently querying a remote server to retrieve information about images captured by a mobile device. In addition to reduced transmission overhead and computational complexity, the retrieval protocol should be robust to variations in the image acquisition process, such as translation, rotation, scaling, and sensor-related differences. We propose to ex- tract scale-invariant image features and then perform clustering to reduce the number of features needed for image matching. Principal Component Analysis (PCA) and Non-negative Matrix Factorization (NMF) are investigated as candidate clustering approaches. The im- age matching complexity at the database server is quadratic in the (small) number of clusters, not in the (very large) number of im- age features. We employ an image-dependent information content metric to approximate the model order, i.e., the number of clus- ters, needed for accurate matching, which is preferable to setting the model order using trial and error. We show how to combine the hypotheses provided by PCA and NMF factor loadings, thereby ob- taining more accurate retrieval than using either approach alone. In experiments on a database of urban images, we obtain a top-1 re- trieval accuracy of 89% and a top-3 accuracy of 92.5%.