Mitigating effects of plastic surgery: Fusing face and ocular biometrics

Jillela, Raghavender; Ross, Arun

doi:10.1109/btas.2012.6374607

Cited by 46 publications

(31 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, the number of gallery subjects and probe im- ages used in each algorithm is illustrated for a better comparison. In [4], 661 pre-surgery images from the plastic surgery database and 568 images from the FRGC database 3 are used to form the gallery set, while the query images are the corresponding 661 post-surgery images. Verilook 3.2 is a commercial software from Neurotechnology 4 .…”

Section: Resultsmentioning

confidence: 99%

“…These images were collected from plastic surgery information websites, hence, many present a number of non-ideal fac- tors such as duplicate entries, incomplete faces and nonfrontal faces. Similarly to the pre-selection procedure used in [4], we excluded images which show the above negative factors. Finally, a dataset consisting of 1, 576 images from 784 subjects was selected, i.e., N = 784.…”

Section: Methodsmentioning

confidence: 99%

“…In the related work, a sequestered face image set was used to fulfill the multiple image requirement of sparse representation approach. In [4], a fusion approach by combining information from both the whole face and the ocular regions [10] was proposed to deal with the challenges of matching faces across variations caused by plastic surgeries. Very recently, Liu et al employed an ensemble of Gabor Patch classifiers via Rank-Order list fusion algorithm and achieved very promising results [6].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Structural Similarity based image quality map for face recognition across plastic surgery

Sun

Tistarelli

Maltoni

2013

2013 IEEE Sixth International Conference on Biometrics: Theory, Applications and Systems (BTAS)

View full text Add to dashboard Cite

Variations in the face appearance caused by plastic surgery on skin texture and geometric structure, can impair the performance of most current face recognition systems. In this work, we proposed to use the Structural Similarity (SSIM) quality map to detect and model variations due to plastic surgeries. In the proposed framework, a S-SIM index weighted multi-patch fusion scheme is developed, where different weights are provided to different patches in accordance with the degree to which each patch may be altered by surgeries. An important feature of the proposed approach, also achieving performance comparable with the current state-of-the-art, is that neither training process is needed nor any background information from other datasets is required. Extensive experiments conducted on a plastic surgery face database demonstrate the potential of SSIM map for matching face images after surgeries.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Structural Similarity based image quality map for face recognition across plastic surgery

Sun

Tistarelli

Maltoni

2013

2013 IEEE Sixth International Conference on Biometrics: Theory, Applications and Systems (BTAS)

View full text Add to dashboard Cite

show abstract

“…Fusion of face and ocular regions is not a new idea, as already pointed out in the recognition problem by [24] and [31]. Here we go further combining multi-scale information as we fuse, facial (F), head and shoulders (HS) and periocular (P) information for GC, see Figure 9.…”

Section: Multi-scale Score Level Fusionmentioning

confidence: 99%

“…Different authors claim that ocular based systems are able to cope with challenging scenarios where the whole face is not available, e.g. partially occluded, or even when available, it has been altered with plastic surgery, as evidenced by [32,29]; and [24].…”

Section: Ocular Gcmentioning

confidence: 99%