Hypercomplex extreme learning machine with its application in multispectral palmprint recognition

• Published in: PloS one Vol. 14; no. 4; p. e0209083
• Main Authors: Lu, Longbin, Zhang, Xinman, Xu, Xuebin
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 15.04.2019; Public Library of Science (PLoS)
• Subjects: Adult; Algorithms; Artificial intelligence; Artificial neural networks; Biology and Life Sciences; Biometric identification; Biometrics; Biometry; Classification; Computer and Information Sciences; Dermatoglyphics; Downloading; Engineering and Technology; Feedforward; Female; Fourier transforms; Humans; Learning; Learning algorithms; Machine Learning; Male; Methods; Middle Aged; Musical groups; Neural networks; Neural Networks, Computer; Novels; Object recognition; Pattern recognition (Computers); Pattern Recognition, Automated - methods; Physical Sciences; Principal components analysis; Remote sensing; Research and Analysis Methods; Sensors; Source code; Spectral bands; Teaching methods; Theory; Young Adult; China
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0209083

An extreme learning machine (ELM) is a novel training method for single-hidden layer feedforward neural networks (SLFNs) in which the hidden nodes are randomly assigned and fixed without iterative tuning. ELMs have earned widespread global interest due to their fast learning speed, satisfactory generalization ability and ease of implementation. In this paper, we extend this theory to hypercomplex space and attempt to simultaneously consider multisource information using a hypercomplex representation. To illustrate the performance of the proposed hypercomplex extreme learning machine (HELM), we have applied this scheme to the task of multispectral palmprint recognition. Images from different spectral bands are utilized to construct the hypercomplex space. Extensive experiments conducted on the PolyU and CASIA multispectral databases demonstrate that the HELM scheme can achieve competitive results. The source code together with datasets involved in this paper can be available for free download at https://figshare.com/s/01aef7d48840afab9d6d.