Search research articles

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

Dental age assessment: orthopantomogram-based comparison of traditional methods and artificial intelligence in the adult population.

International journal of legal medicine·2026

Same author

A Pilot Study on AI-Driven Age Estimation and Sex Determination in Greek Individuals.

Journal of imaging·2026

Same author

Dense Out-of-Distribution Detection by Robust Learning on Synthetic Negative Data.

Sensors (Basel, Switzerland)·2024

Same author

Detection and Segmentation of Radiolucent Lesions in the Lower Jaw on Panoramic Radiographs Using Deep Neural Networks.

Medicina (Kaunas, Lithuania)·2023

Same author

Artificial Intelligence in Medicine and Dentistry.

Acta stomatologica Croatica·2023

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 Video

Updated: Jul 10, 2026

Spotlighting Customers' Visual Attention at the Stock, Shelf and Store Levels with the 3S Model

Spotlighting Customers' Visual Attention at the Stock, Shelf and Store Levels with the 3S Model

Published on: May 24, 2019

Enhanced Out-of-Stock Detection in Retail Shelf Images Based on Deep Learning.

Franko Šikić¹, Zoran Kalafatić¹, Marko Subašić¹

¹Image Processing Laboratory, Faculty of Electrical Engineering and Computing, University of Zagreb, 10000 Zagreb, Croatia.

Sensors (Basel, Switzerland)

|January 26, 2024

Summary

This summary is machine-generated.

A new deep learning method accurately detects out-of-stock (OOS) products on shelves. This approach improves sales and customer loyalty by identifying both empty shelves and frontal OOS instances.

Keywords:

deep learning image analysis image processing out-of-stock detection

More Related Videos

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

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: Jul 10, 2026

Spotlighting Customers' Visual Attention at the Stock, Shelf and Store Levels with the 3S Model

Spotlighting Customers' Visual Attention at the Stock, Shelf and Store Levels with the 3S Model

Published on: May 24, 2019

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

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
Retail Technology

Background:

Out-of-stock (OOS) instances lead to significant sales losses and damage retailer reputation.
Accurate detection of OOS products is crucial for inventory management and customer satisfaction.

Purpose of the Study:

To propose a novel deep learning (DL)-based method for detecting out-of-stock (OOS) products.
To enhance OOS detection accuracy by addressing both fully empty and frontal OOS scenarios.

Main Methods:

A two-stage training process involving pre-training on augmented data and fine-tuning on original data.
A new image augmentation technique that enlarges OOS instances by mirroring them onto adjacent products.
A post-processing step that filters detections based on aspect ratio to remove inaccuracies.

Main Results:

The proposed DL method achieved high average precision for detecting fully empty OOS instances (86.3%) and frontal OOS instances (83.7%).
The method demonstrated superior performance compared to existing DL-based OOS detection techniques.
The novel augmentation and post-processing techniques effectively improved detection accuracy.

Conclusions:

The developed DL-based OOS detection method offers a significant advancement in identifying missing products on retail shelves.
This approach can help retailers minimize sales losses and enhance customer experience.
The findings suggest the potential for widespread adoption in retail inventory management systems.