Automatic image annotation

Abstract

An automatic image annotation system receives a reference image with one or more parts annotated along with one or more query images and automatically identifies portions from the query images that are similar to the annotated parts of the reference image. The S-matrices of the reference image and the query images are obtained via singular value decomposition (SVD). Lower-dimensional images are also obtained for the reference image and the query images using a pre-trained deep learning model. The S-matrices and the lower-dimensional images of the corresponding images are combined to generate vector representations. A distance metric is calculated for the vector representation of the reference image with that of the query image. A preliminary output image with a preliminary annotation is initially generated. The preliminary annotation is further optimized to generate an optimized annotation that adequately covers the region of interest (ROI).