Robust local binary pattern feature sets for periocular biometric identification

Xu, Juefei; Cha, Miriam; Heyman, Joseph L.; Venugopalan, Shreyas; Abiantun, Ramzi; Savvides, Marios

doi:10.1109/btas.2010.5634504

Cited by 64 publications

(33 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They performed experiments on the Face and FOCS database [30] which contains periocular region appearance variations in the form of illumination, blur and off-angle iris. They reported better recognition rates of the ocular [16]. Pauca et al [32] used SIFT features for classification of the periocular regions and also introduced the COIR database.…”

Section: Survey Of Periocular Biometrics Researchmentioning

confidence: 99%

“…They used the visible spectrum eye images of UBIIRIS v2 [28] dataset which contained slight appearance variations. Xu et al [16] proposed Walsh Transform based local binary patterns (WLBP). Periocular region containing both eyes were cropped using the detected iris centers.…”

Section: Survey Of Periocular Biometrics Researchmentioning

confidence: 99%

“…Previous works on periocular biometrics are mostly based on single image matching [11,12,13,14,15,16] where a single best frame per subject is handpicked to form the gallery. Each image in the query sequence is matched with the gallery to find the best match.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Periocular region-based person identification in the visible, infrared and hyperspectral imagery

et al. 2015

View full text Add to dashboard Cite

Face recognition performance degrades significantly under occlusions that occur intentionally or unintentionally due to head gear or hair style. In many incidents captured by surveillance videos, the offenders cover their faces leaving only the periocular region visible. We present an extensive study on periocular region based person identification in video. While, previous techniques have handpicked a single best frame from videos, we formulate, for the first time, periocular region based person identification in video as an image-set classification problem. For thorough analysis, we perform experiments on periocular regions extracted automatically from RGB videos, NIR videos and hyperspectral image cubes. Each image-set is represented by four heterogeneous feature types and classified with six state-of-the-art image-set classification algorithms. We propose a novel two stage inverse Error Weighted Fusion algorithm for feature and classifier score fusion. The proposed two stage fusion is superior to single stage fusion. Comprehensive experiments were performed on four standard datasets, MBGC NIR and visible spectrum [1], CMU Hyperspectral [2] and UBIPr [3]. We obtained average rank-1 recognition rates of 99.8, 98.5, 97.2, and 99.5% respectively which are significantly higher than the existing state of the art. Our results demonstrate the feasibility of image-set based periocular biometrics for real world applications.

show abstract

Section: Survey Of Periocular Biometrics Researchmentioning

confidence: 99%

Section: Survey Of Periocular Biometrics Researchmentioning

confidence: 99%

See 1 more Smart Citation

Periocular region-based person identification in the visible, infrared and hyperspectral imagery

et al. 2015

View full text Add to dashboard Cite

show abstract

“…Xu et al [22] observed improvements in recognition rates by combining LBP with other features including DCT, DWT, Gabor filters, LoG filters, Walsh transform [8], SIFT, and SURF. Woodard et al [21] simultaneously used the iris and periocular biometrics by performing score-level fusion.…”

Section: Related Work On Periocular Biometricsmentioning

confidence: 99%

“…Most of the previous work on periocular biometric recognition is based on single image matching [5,20,21,2,22]. In many cases, a single best frame per subject is manually selected and placed in the gallery.…”

Section: Introductionmentioning

confidence: 99%

Periocular biometric recognition using image sets

Uzair

Mahmood

Mian

et al. 2013

2013 IEEE Workshop on Applications of Computer Vision (WACV)

View full text Add to dashboard Cite

Human identification based on iris biometrics requires high resolution iris images of a cooperative subject. Such images cannot be obtained in non-intrusive applications such as surveillance. However, the full region around the eye, known as the periocular region, can be acquired nonintrusively and used as a biometric. In this paper we investigate the use of periocular region for person identification. Current techniques have focused on choosing a single best frame, mostly manually, for matching. In contrast, we formulate, for the first time, person identification based on periocular regions as an image set classification problem. We generate periocular region image sets from the Multi Biometric Grand Challenge (MBGC) NIR videos. Periocular regions of the right eyes are mirrored and combined with those of the left eyes to form an image set. Each image set contains periocular regions of a single subject. For imageset classification, we use six state-of-the-art techniques and report their comparative recognition and verification performances. Our results show that image sets of periocular regions achieve significantly higher recognition rates than currently reported in the literature for the same database.

show abstract