Abstract
AbstractA novel image palmprint reconstruction method using the combined method of bi-dimensional empirical mode decomposition (BEMD) and weight coding based non-negative sparse coding (WCB-NNSC) is proposed here. The BEMD algorithm is especially adaptive for non-linear and non-stationary 2D-data analysis. And the weight coding based NNSC algorithm includes more class information than that of the basic NNSC. For each original palmprint image, its first two order high frequency intrinsic mode functions (IMFs) extracted by BEMD are denoised by Wiener filter, then denosied IMFs and low frequency IMFs are fused by weighted method and normalized, moreover, using these preprocessed images as test images of WCB-NNSC, and feature basis vectors can be successfully learned Moreover, using suitable classifiers, the palmprint recognition task can be implemented. Further, in the same experimental condition, compared with palmprint feature recognition methods of standard ICA and NNSC, Simulation results show that our method proposed in this paper is indeed efficient and effective in performing palmprint recognition task.KeywordsBEMD methodWeight codingNon-negative sparse coding (NNSC)Palmprint imagesFeature recognition
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
