Periocular and iris local descriptors for identity verification in mobile applications

Aginako, Naiara; Castrillón-Santana, Modesto; Lorenzo-Navarro, Javier; Martínez-Otzeta, José María; Sierra, Basilio

doi:10.1016/j.patrec.2017.01.021

Cited by 21 publications

(12 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A common preprocessing step is division of the periocular region into sub-blocks in rows and columns for global feature analysis, 6x8 [10], 7x5 [2], multiple sub-block configurations were used in [4] [8]. Images are rescaled to suitable dimensions: 100x160 [18], 128x168 [3], 49x19 [8], 20x30 [6], 32x49 [40], image cropping [42] and image padding [39].…”

Section: Periocular Image Segmentation and Preprocessing Methodsmentioning

confidence: 99%

“…Images are characterized by light reflections, occlusion, out-of-focus blur, off-axis gaze, variance in illumination and devicespecific artifacts. MICHE-II has samples from 86 individuals [4].…”

Section: Databases For Periocular Recognition Researchmentioning

confidence: 99%

“…[55]. LPQ was employed in the work of [4]. It was also used by Indian Institute of Technology (IIT) Indore, India in the Cross-Eyed2017 competition [38].…”

Section: Local Phase Quantizationmentioning

confidence: 99%

“…Thus, WLD is a measure of change in intensity with reference to a center pixel and the gradient orientation. WLD was used in the work of [4] [8].…”

Section: Weber Local Descriptorsmentioning

confidence: 99%

“…It includes the eyebrows, upper and lower eyelids, sclera, skin texture and color, blood vessels, tear duct, inner corner, outer corner, upper and lower eye folds and eye lashes, as shown in Fig.1 [1]. Periocular recognition, like similar biometric recognition systems, can be adopted as a means of personal authentication to ensure authorized access to sensitive information as required for smartphones [2] [3], for access control to sensitive units like switch rooms in organizations and in financial and payment applications where user identification is necessary for optimal security [4].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Survey of Periocular Recognition Techniques

Badejo¹,

Akinrinmade²,

Adetiba³

2019

JESTR

View full text Add to dashboard Cite

Periocular recognition has evolved over the years and has been shown to possess discriminative features for personal identification either as a stand-alone trait or when fused with other modalities such as face and iris, especially in unconstrained scenarios. It has a number of advantages, first being the region could be easily cropped from existing face images. Secondly, unlike the iris, its capturing process is less intrusive. This area of the face is easily captured with ease from the subject, for example by surveillance cameras. Thirdly, in crime scenes where masks hide the face or in cases where the subject's face is covered due to religious or cultural beliefs, the periocular region could still be captured providing useful details, that is, it is robust to face occlusion and is least affected by expression change. This survey relates the various techniques employed for periocular recognition at different stages: segmentation approaches, image preprocessing methods, feature extraction and matching algorithms. This survey is meant to facilitate a quick grasp of the development in this area for interested students, researchers as well as enthusiasts in the field of biometrics or any related application area. Information about the various databases used for performance evaluation of these techniques as well as the performance indicators is also provided.

show abstract

Section: Periocular Image Segmentation and Preprocessing Methodsmentioning

confidence: 99%

Section: Databases For Periocular Recognition Researchmentioning

confidence: 99%

“…[55]. LPQ was employed in the work of [4]. It was also used by Indian Institute of Technology (IIT) Indore, India in the Cross-Eyed2017 competition [38].…”

Section: Local Phase Quantizationmentioning

confidence: 99%

“…Thus, WLD is a measure of change in intensity with reference to a center pixel and the gradient orientation. WLD was used in the work of [4] [8].…”

Section: Weber Local Descriptorsmentioning

confidence: 99%