Search research articles

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

Biomechanical Analysis of the Field Hockey Sweep Skill Using Inertial Measurement Units.

Sensors (Basel, Switzerland)·2026

Same author

Simplifying Prediction of Intended Grasp Type: Accelerometry Performs Comparably to Combined EMG-Accelerometry in Individuals With and Without Amputation.

Sensors (Basel, Switzerland)·2025

Same author

Feasibility Study for Wearable Sensor-Based Vibrotactile Feedback for Posture and Muscle Activation in a Relevant Dentistry Setting.

Sensors (Basel, Switzerland)·2025

Same author

Assessing Vibrotactile Feedback Effects on Posture, Muscle Recruitment, and Cognitive Performance.

Sensors (Basel, Switzerland)·2025

Same author

A simulation study to investigate an extension to the point cluster technique.

Scientific reports·2023

Same author

Effects of Concurrent and Terminal Visual Feedback on Ankle Co-Contraction in Older Adults during Standing Balance.

Sensors (Basel, Switzerland)·2021

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: Jan 12, 2026

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

A Comprehensive Dataset for Image Segmentation in Custom Manufacturing Environments.

Martell Bell¹, Rachel V Vitali²

¹University of Iowa, Department of Mechanical Engineering, Iowa City, 52242, US. martell-bell@uiowa.edu.

Scientific Data

|October 31, 2025

Summary

This study introduces a new image dataset for automating sprue and riser removal in high-mix, low-volume (HMLV) foundries using machine learning. The open-source dataset aids in developing robust industrial imaging models for process automation.

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

Published on: May 24, 2022

Related Experiment Videos

Last Updated: Jan 12, 2026

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

Published on: May 24, 2022

Area of Science:

Industrial Automation
Computer Vision
Materials Science

Background:

High-mix, low-volume (HMLV) foundries face automation challenges.
Industry 4.0 offers potential solutions, especially in process automation.
Automating post-processing tasks like sprue and riser removal is crucial for efficiency.

Purpose of the Study:

To develop a comprehensive image dataset for training neural networks.
To automate sprue and riser removal in sand-cast parts.
To address the variability in HMLV environments through diverse image data.

Main Methods:

Creation of a novel image dataset including real, synthetic, and augmented images.
Systematic evaluation of image quality metrics and their impact on model training.
Development of an image segmentation neural network for automated post-processing.

Main Results:

The dataset captures diverse part representations and scene complexity.
Image quality metrics were evaluated for their impact on model performance.
The approach addresses variability inherent in HMLV manufacturing.

Conclusions:

The developed dataset is a valuable resource for machine learning in industrial imaging.
The approach enhances the robustness of models in complex industrial settings.
The complete dataset and code are publicly available as an open-source resource.