Partially Occluded Face Reconstruction Using Graph-based Algorithm

This study introduces a novel algorithm rooted in spectral graph theory for the reconstruction of occluded facial images, with the aim of enhancing face recognition accuracy. The proposed method, Face Reconstruction using Graph Fourier Transform (FRGFT) comprises three key stages: firstly, construct...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Journal of electrical engineering & technology Ročník 19; číslo 6; s. 3655 - 3664
Hlavní autoři: Meena, Manisha Kumari, Meena, Hemant Kumar, Sharma, Ramnivas
Médium: Journal Article
Jazyk:angličtina
Vydáno: Singapore Springer Nature Singapore 01.08.2024
Springer Nature B.V
대한전기학회
Témata:
Electrical Engineering
Electrical Machines and Networks
Electronics and Microelectronics
Engineering
Instrumentation
Original Article
Power Electronics
전기공학
Face reconstruction
Graph Fourier transform (GFT)
Occlusion detection
Structural similarity index
Peak signal-to-noise ratio
Graph segmentation
ISSN:1975-0102, 2093-7423
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:This study introduces a novel algorithm rooted in spectral graph theory for the reconstruction of occluded facial images, with the aim of enhancing face recognition accuracy. The proposed method, Face Reconstruction using Graph Fourier Transform (FRGFT) comprises three key stages: firstly, construct a graph representation of the image where each pixel is a node, and edges between nodes represent pixel adjacency with weights that capture both intensity and spatial relationships; secondly, identify occluded parts of the image using a graph-based segmentation technique to update the occlusion mask; and thirdly, reconstruct the original image from the occluded version using the Laplacian matrix of the graph and the updated occlusion mask. The whole process lies on the Graph Laplacian (GL) technique, which draws the concepts from graphical models and the Laplace equation, proving to be effective in the high-quality restoration of faces that are damaged or occluded. This paper establishes the connection between GL and the traditional Fourier transform methods. To assess the utility of the GL-based restoration, completed facial images processed through the algorithm are subjected to face recognition testing. The effectiveness of the proposed approach is validated on two datasets: extended AR and CelebA face dataset, which have been significantly noticeable as our proposed approach achieves 98.5% accuracy as compared with the existing method.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1975-0102
2093-7423
DOI:10.1007/s42835-024-01995-5