English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In this paper, we propose a novel method for fast face recognition calledL1/2 Regularized Sparse Representation using Hierarchical Feature Selection(HSR). By employing hierarchical feature selection, we can compress the scaleand dimension of global dictionary, which directly contributes to the decreaseof computational cost in sparse representation that our approach is stronglyrooted in. It consists of Gabor wavelets and Extreme Learning MachineAuto-Encoder (ELM-AE) hierarchically. For Gabor wavelets part, local featurescan be extracted at multiple scales and orientations to form Gabor-featurebased image, which in turn improves the recognition rate. Besides, in thepresence of occluded face image, the scale of Gabor-feature based globaldictionary can be compressed accordingly because redundancies exist inGabor-feature based occlusion dictionary. For ELM-AE part, the dimension ofGabor-feature based global dictionary can be compressed becausehigh-dimensional face images can be rapidly represented by low-dimensionalfeature. By introducing L1/2 regularization, our approach can produce sparserand more robust representation compared to regularized Sparse Representationbased Classification (SRC), which also contributes to the decrease of thecomputational cost in sparse representation. In comparison with related worksuch as SRC and Gabor-feature based SRC (GSRC), experimental results on avariety of face databases demonstrate the great advantage of our method forcomputational cost. Moreover, we also achieve approximate or even betterrecognition rate.

HSR: L1/2 Regularized Sparse Representation for Fast Face Recognition using Hierarchical Feature Selection