RelMS

AcronymDefinition
RelMSRelocation Management Systems
RelMSRapidly Erectable Light Mobilization Structures
Copyright 1988-2018 AcronymFinder.com, All rights reserved.
References in periodicals archive ?
Algorithm 1: Multispectral palmprint classification based on RELM. Input: the compressed features of AE for training and testing sets and parameters' values Output: the users' IDs of the testing dataset Training phase: (1) Initialization step: (i) Assign random values for the weights and biases of RELM (2) Computational step: (i) Compute the matrix, H of the hidden layer using Eq.
To show the effectiveness of the proposed approach based on AE and RELM using NGist features over the features of the original Gist, we computed the recognition rates using extracted features of both descriptors at different numbers of RELM's hidden nodes.
Moreover, the advantages of AE to deal with the nonlinearity of features and RELM to solve the overfitting problem made the power of the proposed approach.
Actually, the robustness of NGist descriptor with AE and RELM handles this challenge effectively.
A novel multispectral palmprint recognition approach is proposed based on AE and RELM with an efficient extended version of Gist descriptor, named NGist.
Caption: Figure 4: Recognition rates of blue spectral band using different numbers of RELM's hidden nodes.
Caption: Figure 5: Recognition rates of green spectral band using different numbers of RELM's hidden nodes.
Caption: Figure 6: Recognition rates of red spectral band using different numbers of RELM's hidden nodes.
Caption: Figure 7: Recognition rates of NIR spectral band using different numbers of RELM's hidden nodes.
Caption: Figure 9: Recognition rates of green spectral band using extracted features of NGist and Gist at different numbers of RELM's hidden nodes.
Caption: Figure 10: Recognition rates of red spectral band using extracted features of NGist and Gist at different numbers of RELM's hidden nodes.
Caption: Figure 11: Recognition rates of NIR spectral band using extracted features of NGist and Gist at different numbers of RELM's hidden nodes.