Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

Shared feature extraction for nearest neighbor face recognition.

D Masip¹, J Vitria

¹Universitat Oberta de Catalunya, Barcelona, Spain. dmasipr@uoc.edu

IEEE Transactions on Neural Networks

|April 9, 2008

Summary

This study introduces a novel supervised linear feature extraction method for multiclass classification, enhancing nearest neighbor (NN) classifiers. The technique, utilizing Adaboost and multitask learning (MTL), excels in small sample size scenarios like face recognition.

Related Concept Videos

Association Areas of the Cortex

Association Areas of the Cortex

Association areas are regions of the cerebral cortex that do not have a specific sensory or motor function. Instead, they integrate and interpret information from various sources to enable higher cognitive processes such as memory, learning, and decision-making. Some key association areas include the following:
Prefrontal Association Area: This area is located in the frontal lobe and is involved in planning, decision-making, and moderating social behavior. It connects with primary motor areas,...

Extraction: Advanced Methods

Extraction: Advanced Methods

Metal ions can be separated from one another by complexation with organic ligands–the chelating agent– to form uncharged chelates. Here, the chelating agent must contain hydrophobic groups and behave as a weak acid, losing a proton to bind with the metal. Since most organic ligands used in this process are insoluble or undergo oxidation in the aqueous phase, the chelating agent is initially added to the organic phase and extracted into the aqueous phase. The metal-ligand complex is formed in...

You might also read

Related Articles

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

Sort by

Same author

Automated gesture tracking in head-fixed mice.

Journal of neuroscience methods·2017

Same author

Functional gut disorders or disordered gut function? Small bowel dysmotility evidenced by an original technique.

Neurogastroenterology and motility·2011

Same author

Intestinal motor activity, endoluminal motion and transit.

Neurogastroenterology and motility·2009

Same author

Clustering in image space for place recognition and visual annotations for human-robot interaction.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2008

Same author

Automated classification of renal interstitium and tubules by local texture analysis and a neural network.

Analytical and quantitative cytology and histology·1996

Same author

Automatic evaluation of renal interstitial volume fraction.

Transplantation proceedings·1995

Area of Science:

Machine Learning
Computer Vision
Pattern Recognition

Background:

Nearest Neighbor (NN) classifiers require effective feature extraction for optimal performance.
Traditional methods often struggle with high-dimensional data and limited sample sizes.
Supervised linear feature extraction is crucial for improving classification accuracy.

Purpose of the Study:

To develop a new supervised linear feature extraction technique tailored for multiclass classification problems.
To enhance the performance of Nearest Neighbor (NN) classifiers, particularly in small sample size scenarios.
To integrate multitask learning (MTL) into the feature extraction process.

Main Methods:

The proposed method defines the optimal linear projection matrix as a classification problem.

Related Experiment Videos

Adaboost algorithm is employed iteratively to compute the projection matrix.

A multitask learning (MTL) criterion is incorporated, making no assumptions about data distribution.

Main Results:

The technique effectively addresses the small sample size problem.
Experiments on face recognition demonstrate improved performance compared to classic feature extraction algorithms.
The multitask approach yields superior representations for NN classifiers with limited data per class.

Conclusions:

The novel supervised linear feature extraction method significantly enhances NN classifier performance.
The integration of Adaboost and MTL offers a robust solution for multiclass classification with small sample sizes.
This approach provides a powerful tool for applications like face recognition where data is often limited.