Weighted group sparse representation for undersampled face recognition

Locality-constrained group sparse coding regularized NMR for robust face recognition

“…From Table 1 and Figure 2, the proposed LGNMR outperforms those pixel-based regression methods though it is little higher than NMR, which is consistant with the results in [11]. The recognition rate of LGNMR increases to 96.5% whereas NMR is 96.1% in Table 1.…”

“…However, NMR also do not utilize the label information and the group structure of training samples. As we know, to address the mentioned second disadvantage, some group sparse representation based classification (GSRC) methods have been produced by considering the label information, such as [10] [11]. The training samples within a group have the same label.…”

A survey on representation-based classification and detection in hyperspectral remote sensing imagery

“…It turns out that the weighted version outperforms the original SOMP and JCRC. In [56,57,58,59], weighted sparse representation and locality-constrained collaborative representations were discussed. Another strategy is based on a prior segmentation map [60] where only within-segment pixels are used in the generation of the smoothed version of y.…”

A coarse-to-fine model for airport detection from remote sensing images using target-oriented visual saliency and CRF

“…As there are many airport-confused objects in large remote sensing images, features mentioned above may result in an insufficient description of airports. Recent developments have shown the effectiveness of using learning sparse representations in the context of face recognition [17,18], image denoising [19], image classification [20][21][22], and hyperspectral imagery analysis [23]. The sparse representation can capture more salient properties of visual patterns, which is suitable to describe airports robustly.…”