Paper Info
Title
Image Set Classification for Low Resolution Surveillance.
Abstract
This paper proposes a novel image set classification technique based on the concept of linear regression. Unlike most other approaches, the proposed technique does not involve any training or feature extraction. The gallery image sets are represented as subspaces in a high dimensional space. Class specific gallery subspaces are used to estimate regression models for each image of the test image set. Images of the test set are then projected on the gallery subspaces. Residuals, calculated using the Euclidean distance between the original and the projected test images, are used as the distance metric. Three different strategies are devised to decide on the final class of the test image set. We performed extensive evaluations of the proposed technique under the challenges of low resolution, noise and less gallery data for the tasks of surveillance, video based face recognition and object recognition. Experiments show that the proposed technique achieves a better classification accuracy and a faster execution time under the challenging testing conditions.
Year
Venue
Field
2018
arXiv: Computer Vision and Pattern Recognition
Facial recognition system,Pattern recognition,Computer science,Euclidean distance,Metric (mathematics),Feature extraction,Linear subspace,Artificial intelligence,Standard test image,Cognitive neuroscience of visual object recognition,Test set
DocType
Volume
Citations 
Journal
abs/1803.09470
0
PageRank 
References 
Authors
0.34
22
5
Name
Order
Citations
PageRank
Uzair Nadeem100.34
Syed Afaq Ali Shah29015.23
M. Bennamoun33197167.23
Roberto Togneri481448.33
Ferdous Ahmed Sohel562331.78