Discovering common visual patterns (CVPs) from two images is a challenging task due to the geometric and photometric deformations as well as noises and clutters. The problem is generally boiled down to recovering correspondences of local invariant features, and the conventionally addressed by graph-based quadratic optimization approaches, which often suffer from high computational cost. In this paper, we propose an efficient approach by viewing the problem from a novel perspective. In particular, we consider each CVP as a common object in two images with a group of coherently deformed local regions. A geometric space with matrix Lie group structure is constructed by stacking up transformations estimated from initially appearance-matched local interest region pairs. This is followed by a mean shift clustering stage to group together those close transformations in the space. Joining regions associated with transformations of the same group together within each input image forms two large regions sharing similar geometric configuration, which naturally leads to a CVP. To account for the non-Euclidean nature of the matrix Lie group, mean shift vectors are derived in the corresponding Lie algebra vector space with a newly provided effective distance measure. Extensive experiments on single and multiple common object discovery tasks as well as near-duplicate image retrieval verify the robustness and efficiency of the proposed approach.
The effect of the quenched speed on the microstructure and electromagnetic properties of melt spun Nd3Fe68Co18B11 nanocomposites was investigated. XRD spectra showed that only α-Fe phase can be obtained for both quenched samples. The complex permeability () and permittivity () within 2-18GHz were measured by vector network analysis. By virtue of quenched speed increased, the flake-like Nd3Fe68Co18B11 decreased the value of permittivity while that of permeability slightly changed. According to transmission line theory, the reflection loss was calculated. With thin matching thickness of 1.5mm, The Nd3Fe68Co18B11 composites realized the optimum reflection loss RL=-5.3dB at 3.6GHz and RL=-3.5dB at 3.9GHz for quenched speed 30m/s and 20m/s, respectively. It showed that it is possible to obtain good microwave absorbing properties with appreciated quenched speed for as spun Nd-Fe-B nanocomposites.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.