Robust and adaptive algorithm for hyperspectral palmprint region of interest extraction

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.