Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Face recognition using the nearest feature line method.

S Z Li1, J Lu

  • 1School of EEE, Nanyang Technological University, BLK S1, Singapore.

IEEE Transactions on Neural Networks
|February 7, 2008
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Solution structure of cytochrome b(5) mutant (E44/48/56A/D60A) and its interaction with cytochrome c.

European journal of biochemistry·2001
Same author

[Changes of nitric oxide synthase in hypoxic pulmonary hypertension and the effect of L-arg and L-NAME on pulmonary circulation].

Zhonghua bing li xue za zhi = Chinese journal of pathology·2001
Same author

Clinical study on reservation of part of stomach for patients with cardiac cancer of the gastric stump.

Chinese medical journal·2001
Same author

Localization of the K(+)-Cl(-) cotransporter, KCC3, in the central and peripheral nervous systems: expression in the choroid plexus, large neurons and white matter tracts.

Neuroscience·2001
Same author

[Construction of a human factor VIII gene-containing plasmid and its expression in Cos-7 cells].

Zhonghua xue ye xue za zhi = Zhonghua xueyexue zazhi·2001
Same author

Inhibition of N-nitrosomethylbenzylamine-induced tumorigenesis in the rat esophagus by dietary freeze-dried strawberries.

Carcinogenesis·2001
Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013
Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011
Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011
Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011
Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011
Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011
See all related articles

We introduce the nearest feature line (NFL) method for improved face recognition. NFL significantly reduces error rates compared to standard eigenface methods, achieving state-of-the-art results on the ORL face database.

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Image Processing

Background:

  • Face recognition is a critical area in computer vision.
  • Existing methods like eigenface have limitations in capturing face variations.
  • A need exists for more robust and accurate face classification techniques.

Purpose of the Study:

  • To propose a novel classification method for face recognition.
  • To introduce the nearest feature line (NFL) approach.
  • To demonstrate the effectiveness of NFL in handling face image variations.

Main Methods:

  • The nearest feature line (NFL) method is proposed.
  • Feature lines (FL) are generalized from pairs of feature points of the same class.
  • Classification is performed by measuring the distance from a query feature point to each FL.

Related Experiment Videos

Main Results:

  • The NFL method captures more variations in face images than individual points.
  • NFL expands the capacity of face image databases.
  • Error rates for NFL are 43.7-65.4% lower than the standard eigenface method on a combined database.
  • NFL achieved the lowest reported error rate on the ORL face database.

Conclusions:

  • The nearest feature line (NFL) method offers a significant advancement in face recognition.
  • NFL demonstrates superior performance and accuracy compared to existing methods.
  • This approach holds promise for enhancing the robustness of face recognition systems.