Embedding vector field into image features to enhance classification

DOI10.1016/J.CAM.2023.115685MaRDI QIDQ6145209zbMATH OpenFDO

Authors Nikolay Metodiev Sirakov, Adam Bowden, Mengzhe Chen, L. H. Ngo, Marie Luong

Publication date 30 January 2024

Published in Journal of Computational and Applied Mathematics (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/J.CAM.2023.115685

zbMATH Keywords

featuresgradient vector fieldsPoisson equationsparse representation classification

Mathematics Subject Classification ID

PDEs in connection with information and communication (35Q94) Pattern recognition, speech recognition (68T10) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08)

Recommendations

• Feature vector field and feature matching
• Poisson equation solution and its gradient vector field to geometric features detection
• Local Fisher vector encoding method based on k-dense neighborhood algorithm
• Image classification with the Fisher vector: theory and practice
• An image classification algorithm using Markov random field and multiple kernel learning

Cites work

• Active contour directed by the Poisson gradient vector field and edge tracking
• Applications of the Euler-Lagrange Poisson active contour in vector fields, overcoming noise, and line integrals
• Bifurcation analysis and the Conley index in mechanics
• Dynamics of singular complex analytic vector fields with essential singularities. I
• Extraction of singular points from dense motion fields: An analytic approach
• Hamilton-Jacobi skeletons
• Nonlocal via local-nonlinear via linear: a new part-coding distance field via screened Poisson equation
• Singularities of vector fields

This page was built for publication: Embedding vector field into image features to enhance classification

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6145209)