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

Related Concept Videos

Difference from Background: Limit of Detection

Difference from Background: Limit of Detection

The limit of detection (LOD) is the smallest amount of analyte that can be distinguished from the background noise. The LOD value corresponds to the concentration at which the analyte signal is three times larger than the standard deviation of the blank signal. Below this value, the analyte signal cannot be differentiated from the background noise. It is calculated by dividing the calibration slope by 3 times the standard deviation of the blank signals.
The LOD indicates the presence or absence...

You might also read

Related Articles

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

Sort by

Same author

Inhibitory effects of salvianolic acid B on CCl(4)-induced hepatic fibrosis through regulating NF-κB/IκBα signaling.

Journal of ethnopharmacology·2012

Same author

Combined organic-inorganic fouling of forward osmosis hollow fiber membranes.

Water research·2012

Same author

Expression of the human glucokinase gene: important roles of the 5' flanking and intron 1 sequences.

PloS one·2012

Same author

Long term outcome after conservative and surgical treatment of haemorrhagic moyamoya disease.

Journal of neurology, neurosurgery, and psychiatry·2012

Same author

A role for low-abundance miRNAs in colon cancer: the miR-206/Krüppel-like factor 4 (KLF4) axis.

Clinical epigenetics·2012

Same author

Impact of the 2008 US Preventive Services Task Force recommendation to discontinue prostate cancer screening among male Medicare beneficiaries.

Archives of internal medicine·2012

Search research articles

Related Experiment Video

Updated: Mar 30, 2026

Visualization Method for Proprioceptive Drift on a 2D Plane Using Support Vector Machine

Visualization Method for Proprioceptive Drift on a 2D Plane Using Support Vector Machine

Published on: October 27, 2016

Original and Mirror Face Images and Minimum Squared Error Classification for Visible Light Face Recognition.

¹Changchun University of Science and Technology, Changchun 130022, China.

Thescientificworldjournal

|November 18, 2015

Summary

To enhance face recognition, this study improves minimum squared error classification (MSEC) by generating virtual training samples. Mirror faces are used to augment limited datasets, significantly boosting classification accuracy.

More Related Videos

Author Spotlight: Deciphering Electrical Networks Behind Complex Brain Activities and Disorders

Author Spotlight: Deciphering Electrical Networks Behind Complex Brain Activities and Disorders

Published on: November 1, 2024

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Related Experiment Videos

Last Updated: Mar 30, 2026

Visualization Method for Proprioceptive Drift on a 2D Plane Using Support Vector Machine

Visualization Method for Proprioceptive Drift on a 2D Plane Using Support Vector Machine

Published on: October 27, 2016

Author Spotlight: Deciphering Electrical Networks Behind Complex Brain Activities and Disorders

Author Spotlight: Deciphering Electrical Networks Behind Complex Brain Activities and Disorders

Published on: November 1, 2024

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Area of Science:

Computer Science
Artificial Intelligence
Biometrics

Background:

Real-world face recognition is challenged by variations in illumination, expression, and pose.
Limited training samples hinder the performance of traditional methods like minimum squared error classification (MSEC).

Purpose of the Study:

To enhance the accuracy of face recognition systems.
To address the issue of insufficient training data in MSEC for face recognition.

Main Methods:

Augmenting the training dataset by generating virtual 'mirror face' samples from original data.
Integrating these generated mirror faces with the original training samples.
Applying the improved MSEC method to face recognition experiments.

Main Results:

The proposed method demonstrates high accuracy in face classification tasks.
The use of virtual training samples effectively compensates for limited real-world data.
Significant performance improvement in face recognition was observed.

Conclusions:

Generating mirror faces as virtual training samples is an effective strategy to improve MSEC for face recognition.
This approach enhances classification accuracy, particularly when dealing with limited datasets.
The method offers a practical solution for real-world face recognition challenges.