We present a maximum a posteriori solution to problems of accurate registration of blurred images and recovery of an original undegraded image. Our algorithm has the advantage that...
Over the years, researchers in the image analysis community have successfully used various statistical modeling methods to segment, classify, and annotate digital images. In this ...
Direct image registration methods usually treat shadows as outliers. We propose a method which registers images in a 1D shadow invariant space. Shadow invariant image formation is ...
Abstract. The availability of ground-truth flow field is crucial for quantitative evaluation of any optical flow computation method. The fidelity of test data is also important...
This paper presents a new approach for building semantic image indexing and retrieval systems. Our approach is composed of four phases : (1) knowledge acquisition, (2) weakly-super...