.png){kind=icon}
.png){kind=icon}
Return
Non-overlapped blockwise interpolated local binary pattern as periocular feature
.png){kind=icon}
PRE
AI
DOI：10.1007/s11042-020-08708-w.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Most of the prominent features of human face are present in the ocular area, referred as the periocular region. Complex and dense features in these regions makes it a candidate to be used as a biometric trait. This paper discusses an effective method for periocular recognition using non-overlapped blockwise interpolated local binary pattern (iLBP) features. For a given periocular image, an iLBP coded feature image is obtained and further divided into four equal non-overlapping sub-regions. From each sub-region having iLBP pattern, eight bin histogram features are calculated. A single feature vector is formed by concatenating blocked histograms of each non-overlapping region. Binned histogram based feature is also extracted using Phase Intensive Global Pattern (PIGP) features for comparison of results. Experiments are conducted on UBIRIS.v1 and UBIPr.v2 datasets. From the experiments, it is observed that selected histogram feature bins through the proposed approach provide a more compact representation of periocular image and size of the feature vector is also reduced with significant improvement in performance.
Keywords:
Person identification
Periocular recognition
Local binary pattern
Phase intensive global pattern
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
3
Papers:
1.9W
Citations:
3.2W