An Improved Multispectral Palmprint Recognition System Using Autoencoder with Regularized Extreme Learning Machine

Abstract

Multispectral palmprint recognition system (MPRS) is an essential technology for effective human identification and verification tasks. To improve the accuracy and performance of MPRS, a novel approach based on autoencoder (AE) and regularized extreme learning machine (RELM) is proposed in this paper. The proposed approach is intended to make the recognition faster by reducing the number of palmprint features without degrading the accuracy of classifier. To achieve this objective, first, the region of interest (ROI) from palmprint images is extracted by David Zhang's method. Second, an efficient normalized Gist (NGist) descriptor is used for palmprint feature extraction. Then, the dimensionality of extracted features is reduced using optimized AE. Finally, the reduced features are fed to the RELM for classification. A comprehensive set of experiments are conducted on the benchmark MS-PolyU dataset. The results were significantly high compared to the state-of-the-art approaches, and the robustness and efficiency of the proposed approach are revealed.

Palmprint recognition using state‐of‐the‐art local texture descriptors: a comparative study

“…Second, statisticbased methods [11][12][13][14] have been developed either by using local statistics, such as means and variations, which are calculated on small windows upon the image or by using global ones that are computed upon the entire image such as moments and gravity centres. These statistics can be applied to the intensity image or after transforming it into another space [15][16][17]. The third category is given by the subspace-based methods [18][19][20][21][22], where the main idea consists in mapping the original image onto another space which is supposed to have fewer dimensions than the original one.…”

Democratic voting downsampling for coding‐based palmprint recognition

“…When the feature size is large, effective dimensionality reduction technologies, including subspace technologies, can reduce the storage cost and computational complexity of matching. Gumaei et al [19] proposed an efficient normalised Gist descriptor for palmprint feature extraction and used an optimised autoencoder to reduce feature dimensionality. They also employed the optimised autoencoder to reduce the dimensionality of the hybrid features to improve robustness, accuracy and efficiency of palmprint recognition, which were extracted from the histogram of oriented gradients and a steerable Gaussian filter [20].…”

Hypercomplex extreme learning machine with its application in multispectral palmprint recognition

“…Similarly, Xu et al [25] fused the multispectral images using a digital shearlet transform based method and then classified the fused images with the extreme learning machine. Gumaei et al [26] proposed a kind of Gabor-based feature extraction method and employed the optimal spectral band to determine the identities. The same authors [27] further utilized a hybrid feature extraction method named HOG-SGF instead of Gabor-based one to represent the multispectral palmprint images.…”