A method for contactless palm ROI extraction

El-Sayed, Ahmed; Ebeid, Hala M.; Roushdy, Mohamed; Fayed, Zaki T.

doi:10.1109/icces.2016.7821999

Cited by 5 publications

(8 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To obtain the ROI from traditional palm images, most authors located key points in order to locate the centre position of the ROI or to establish a coordinate system. In [31], EL Sayed et al…”

Section: Related Workmentioning

confidence: 99%

Robust and adaptive algorithm for hyperspectral palmprint region of interest extraction

Zhao

Zhang

2019

IET biom.

View full text Add to dashboard Cite

Recently, hyperspectral imaging has attracted more and more considerable research attention because of its discriminative information. This study proposes a robust approach to adaptively extract the hyperspectral palmprint region of interest (ROI) captured by a hyperspectral palmprint acquisition device, which is considered one of the most important stages in palmprint recognition. For different spectral wavelengths, the image has different illuminations and unbalanced shadows. In particular, mean grey values of palm images in different bands have large variations, such that binarisation of the palm image can be considered a challenging task to accurately separate the contour of the palm from the original image. To solve these problems, this study proposes an adaptive ROI segmentation algorithm, whereby a support vector machine-based method is used to detect the palm from the image and a coordinate established to ensure the accuracy of the ROI. The proposed method has been tested on a hyperspectral palm data set which covers spectrums from 530-1030 nm with 20 nm intervals. The experimental results showed that the proposed algorithm is effective and efficient at locating the ROI in hyperspectral palmprint images, where local binary pattern features were extracted from the ROIs achieving an equal error rate (EER) of 1.49% and an accuracy of 99.51% in recognition.

show abstract

Section: Related Workmentioning

confidence: 99%

Robust and adaptive algorithm for hyperspectral palmprint region of interest extraction

Zhao

Zhang

2019

IET biom.

View full text Add to dashboard Cite

show abstract

“…In the acquisition, the subject places his/her hand with a distance of about 30 cm from the camera. The palm ROI is extracted [7] and resized to 150 × 150.…”

Section: Databasesmentioning

confidence: 99%

“…In this paper, two out of the three used DBs, IITD [10] and GPDS [11], already provide the palm ROI. For the Sfax‐Miracl [40], the method in [7] is used to extract the palm ROI. It takes the hand mask image as an input and passes it through six steps as shown in Fig.…”

Section: Preprocessingmentioning

confidence: 99%

See 1 more Smart Citation

Masked SIFT with align‐based refinement for contactless palmprint recognition

et al. 2018

Self Cite

View full text Add to dashboard Cite

Contactless palmprint is considered more user convenient than other biometrics due to its acquisition simplicity and less-private nature. Many challenges arise which affect the performance of common contact-based methods when applied to a contactless environment. For example, pose and illumination variations affect the layout and visibility of palm lines. This study proposes a SIFT-based method with three main modifications from the traditional SIFT. First, the palm regions with no significant lines/wrinkles are masked out to reduce the false features. A region with multi-lines is then described by multi-descriptors rather than a single one. Second, only query and target keypoints with small rotation difference are compared together, instead of comparing them all. This speed-up the comparison and enhance the accuracy, versus SIFT, by reducing the wrong matches. Third, an align-based refinement is applied to filter out the incorrect matches. The method is tested on three contactless hand databases; IITD, GPDS and Sfax-Miracl. It achieves a verification equal error rate of 0.72, 0.84 and 1.14% and a correct identification rate of 98.9, 99 and 98.9% on each database, respectively. These results are significantly better than the state-ofart methods on the same databases by 1.9% for verification and 3.2% for identification.

show abstract

“…To overcome such challenges, Ito et al [33] propose a novel palm region extraction method which is robust against hand pose variation, but relies on the segmentation from the background, thus making it sensitive to segmentation artefacts. Similarly, the approach of ElSayeed et al [34] relies on uncluttered background and open fingers. Aykut and Ekinci [35] employ an Active Appearance Model (AAM) to extract the Region of Interest (ROI) but only allow one hand posture.…”

Section: Amentioning

confidence: 99%