PATSI|Photo Annotation through Similar Images with Annotation Length Optimization

Automatic Image Annotation (AIA) is an eective technology to improve the performance of images retrieval from large image collections by text queries. In this paper, we propose a novel AIA scheme based on nding the most similar images using a distance metric and then transferring the annotation to the query image. The proposed method can eectively deal with the problem of nding the resulting annotation length. We propose an iterative renement optimization algorithm to nd the best parameters for the annotator. We evaluate the proposed method on two similarity criteria, Minkowski distance and Jensen-Shannon divergence. The proposed solution outperforms the current state-of-the-art methods and could be treated as a new baseline for other automatic image annotation methods.