Multiple clusters parts-based sparse representation for single example face identification

Wang, Bin; Wang, Cungang; Huang, Jingcao

doi:10.1016/j.jvcir.2016.06.019

Cited by 1 publication

(2 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, the single training sample problem brings more challenges to face recognition and is to be worth paying more attention to [42, 43]. Many remarkable algorithms have been proposed: sample enhancement algorithm [44], sample visual expansion algorithm [40, 45–47], general learning framework algorithm [48, 49], feature subspace algorithm [26, 50–55] etc. Some single face sample feature extraction algorithms have been studied and applied to face recognition: multi‐directional orthogonal gradient phase [45], multi‐resolution feature fusion [40], super‐resolution subspace projection [46], joint kernel regression and adaptive dictionary learning [47].…”

Section: Introductionmentioning

confidence: 99%

“…Many remarkable algorithms have been proposed: sample enhancement algorithm [44], sample visual expansion algorithm [40, 45–47], general learning framework algorithm [48, 49], feature subspace algorithm [26, 50–55] etc. Some single face sample feature extraction algorithms have been studied and applied to face recognition: multi‐directional orthogonal gradient phase [45], multi‐resolution feature fusion [40], super‐resolution subspace projection [46], joint kernel regression and adaptive dictionary learning [47]. Some improved local feature extraction algorithms also have been applied to single face recognition: local binary pattern (LBP) pyramid [50, 51], local ternary patterns (LTPs) [52], local structure‐based image decomposition [53], fusion of local normalisation and Gabor entropy weighted features [26], local difference binary [50], scale‐adaptive directional and textural features [55, 56], Weber synergistic centre‐surround pattern [57], orthogonal symmetric local Weber graph structure [58].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Single sample description based on Gabor fusion

2019

View full text Add to dashboard Cite

Owing to lack of enough face image and invalidation of many traditional face recognition algorithms, face recognition with single training sample is really a great challenge. To solve the above problem, this study proposes a novel local weighted fusion Gabor (LWFG) algorithm. First, one single sample is segmented into a series of block sub‐images, and then, each of these sub‐images is decomposed into a series of multi‐resolution Gabor wavelets with multi‐orientation and multi‐scale. Second, different orientation Gabor wavelets with the same scale are fused. Next, different scale Gabor wavelets with the same orientation are fused according to the proposed fusion criterion. Third, the fusion Gabor feature histograms are calculated in each of the divided local regions. Meanwhile, every local region's information importance is measured by the proposed local image information content model. Finally, the fusion Gabor wavelet histograms are adaptively weighed by weighting map which calculated from information content model. This study conducted simulation experiments on different face databases under the different conditions including partial occlusion, expression change and illumination variation. The results indicated that the proposed LWFG algorithm is more effective with single training sample.

show abstract