Unsupervised image matching based on manifold alignment

This paper challenges the issue of automatic matching between two image sets with similar intrinsic structures and different appearances, especially when there is no prior correspondence. An unsupervised manifold alignment framework is proposed to establish correspondence between data sets by a mapping function in the mutual embedding space. We introduce a local similarity metric based on parameterized distance curves to represent the connection of one point with the rest of the manifold. A small set of valid feature pairs can be found without manual interactions by matching the distance curve of one manifold with the curve cluster of the other manifold. To avoid potential confusions in image matching, we propose an extended affine transformation to solve the nonrigid alignment in the embedding space. The comparatively tight alignments and the structure preservation can be obtained simultaneously. The point pairs with the minimum distance after alignment are viewed as the matchings. We apply manifold alignment to image set matching problems. The correspondence between image sets of different poses, illuminations, and identities can be established effectively by our approach.     

Novel similarity measures for face representation based on local binary pattern

The successful face recognition based on local binary pattern(LBP)relies on the effective extraction of LBP features and the inferring of similarity between the extracted features.In this paper,we focus on the latter and propose two novel similarity measures for the local matching methods and the holistic matching methods respectively.One is Earth Mover’s Distance with Hamming and Lp ground distance(EMD-HammingLp),which is a cross-bin dissimilarity measure for LBP histograms.The other is IMage Hamming Distance(IMHD),which is a dissimilarity measure for the whole LBP images.Experiments on FERET database show that the proposed two similarity measures outperform the state-of-the-art Chi-square similarity measure for extraction of LBP features.     

基于稳定区域的形变指纹匹配算法

针对指纹匹配中的非线性形变问题,首次提出了稳定区域的概念,并给出了一种新颖的基于指纹稳定区域的形变指纹匹配算法。通过稳定区域这一概念,巧妙地把指纹匹配问题转化为寻找两幅指纹中对应稳定区域的问题。该算法通过稳定区域的构造、确认和扩张3个步骤,实现了从点到面再到更大区域,从线性形变区域到非线性形变区域的匹配策略。该算法在国际指纹识别竞赛FVC2004的数据库上进行了测试,实验结果表明,该算法有着良好的匹配性能,并有较强的处理非线性形变的能力。     

Glycine-assisted solution combustion synthesis of NiCo2O4 electromagnetic wave absorber with wide absorption bandwidth

Design of high-performance electromagnetic (EM) wave absorbing materials has been regarded as an effective solution to excessive EM wave interference problem. As a promising candidate, NiCo₂O₄ absorbers have attracted enormous research attentions. However, currently reported morphology-manipulation synthetic methods of NiCo₂O₄ absorbers are time-consuming and require high energy consumption, which inhibit their practical applications. Herein, a more facile and cost-effective solution combustion synthesis was utilized to fabricate NiCo₂O₄ materials. The absorber prepared by using glycine as fuel displayed the best EM wave absorption performance. Impressively, ultra wide absorption bandwidth of 7.44 GHz from 10.56 GHz to 18 GHz could be achieved with relatively thin thickness of 2.1 mm NiCo₂O₄ sample fabricated in this work displayed the widest effective absorption bandwidth (EAB) among reported NiCo₂O₄-based EM wave absorbing materials so far. In view of its simple and low-cost synthetic process and excellent EM wave dissipation capacity, NiCo₂O₄ samples in this work showed great feasibility as practical absorber. In addition, our findings may also provide new sight for facile preparation of other high-performance EM wave absorbers by solution combustion synthesis instead of complex morphology-manipulation routes.