Download PDFOpen PDF in browserMulti-source heterogeneous iris recognition using Locality Preserving ProjectionEasyChair Preprint 13868 pages•Date: August 9, 2019AbstractMulti-source heterogeneous iris recognition(MSH-IR) has be- come one of the most challenging hot issues. Iris recognition is too depen- dent on the acquisition device, causing have large intra-class variations, capture iris duplicate data more and more larger. The paper proposed the application of locality preserving projection (LPP) algorithm based on manifold learning as a framework for MSH-IR. Looking for similar in- ternal structures of iris texture, MSH-IR is performed by measuring sim- ilarity. The new solution innovation aspects that LPP algorithm is used to establish the neighboring structure of the similar feature points of the iris texture, and the similarity between the MSH-IR structures is mea- sured after mapping to the low-dimensional space, and using the SVM algorithm to nd and establish the optimal classication hyperplane in low-dimensional space to implement the classication of multi-source het- erogeneous iris images. The experiment based on the JLU-MultiDev iris database. The experimental results demonstrate the eectiveness of the LPP dimension reduction algorithm for MSH-IR. Keyphrases: Iris recognition, LPP, manifold learning, multi-source heterogeneous
|