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 Concept Videos

Reconstruction of Signal using Interpolation01:10

Reconstruction of Signal using Interpolation

552
Signal processing techniques are essential for accurately converting continuous signals to digital formats and vice versa. When a continuous signal is sampled with a period T, the resulting sampled signal exhibits replicas of the original spectrum in the frequency domain, spaced at intervals equal to the sampling frequency. To handle this sampled signal, a zero-order hold method can be applied, which creates a piecewise constant signal by retaining each sample's value until the next...
552

You might also read

Related Articles

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

Sort by
Same author

A systematic review of deep learning-based segmentation techniques for brain tumor detection (2013-2023).

Digital health·2025
Same author

Variational quantum classifier-based early identification and classification of chronic kidney disease using sparse autoencoder and LASSO shrinkage.

PeerJ. Computer science·2025
Same author

Optimized deep learning approach for lung cancer detection using flying fox optimization and bidirectional generative adversarial networks.

PeerJ. Computer science·2025
Same author

Quantum-inspired seagull optimised deep belief network approach for cardiovascular disease prediction.

PeerJ. Computer science·2025
Same author

A comprehensive review of sensor node deployment strategies for maximized coverage and energy efficiency in wireless sensor networks.

PeerJ. Computer science·2024
Same author

Gauss Markov and Flow Balanced Vector Radial Learning network traffic classification on IoT with SDN.

PloS one·2024

Related Experiment Video

Updated: Nov 21, 2025

Transient Optical Clearing Using Absorbing Molecules for Ex Vivo and In Vivo Imaging
07:15

Transient Optical Clearing Using Absorbing Molecules for Ex Vivo and In Vivo Imaging

Published on: July 11, 2025

1.3K

Image Pre-Processing Method of Machine Learning for Edge Detection with Image Signal Processor Enhancement.

Keumsun Park1, Minah Chae1, Jae Hyuk Cho1

  • 1Department of Electronic Engineering, Soongsil University, Seoul 06978, Korea.

Micromachines
|January 14, 2021
PubMed
Summary

This study introduces a machine learning-based pre-processing method to enhance image brightness and contrast for improved edge detection. The new technique significantly boosts edge detection accuracy, outperforming traditional methods.

Keywords:
CMOS image sensoredge detectionimage signal processormachine learningpre-process

More Related Videos

Quantifying Microglia Morphology from Photomicrographs of Immunohistochemistry Prepared Tissue Using ImageJ
08:44

Quantifying Microglia Morphology from Photomicrographs of Immunohistochemistry Prepared Tissue Using ImageJ

Published on: June 5, 2018

71.0K
PIPEMAT-RS: Development and Validation of a Standardized MATLAB Pipeline for Resting-State EEG Preprocessing
06:51

PIPEMAT-RS: Development and Validation of a Standardized MATLAB Pipeline for Resting-State EEG Preprocessing

Published on: June 6, 2025

625

Related Experiment Videos

Last Updated: Nov 21, 2025

Transient Optical Clearing Using Absorbing Molecules for Ex Vivo and In Vivo Imaging
07:15

Transient Optical Clearing Using Absorbing Molecules for Ex Vivo and In Vivo Imaging

Published on: July 11, 2025

1.3K
Quantifying Microglia Morphology from Photomicrographs of Immunohistochemistry Prepared Tissue Using ImageJ
08:44

Quantifying Microglia Morphology from Photomicrographs of Immunohistochemistry Prepared Tissue Using ImageJ

Published on: June 5, 2018

71.0K
PIPEMAT-RS: Development and Validation of a Standardized MATLAB Pipeline for Resting-State EEG Preprocessing
06:51

PIPEMAT-RS: Development and Validation of a Standardized MATLAB Pipeline for Resting-State EEG Preprocessing

Published on: June 6, 2025

625

Area of Science:

  • Computer Vision
  • Image Processing
  • Machine Learning

Background:

  • Edge detection remains a challenge in computer vision due to limitations in Complementary Metal Oxide Semiconductor (CMOS) image sensors and the need for Image Signal Processor (ISP) analysis.
  • Raw image data often suffers from extreme brightness and contrast, hindering effective edge detection.

Purpose of the Study:

  • To propose a novel pre-processing method for optimizing image brightness and contrast to improve edge detection.
  • To enhance the performance of edge detection algorithms by addressing raw image quality issues.

Main Methods:

  • Extracted meaningful features from image data.
  • Applied machine learning algorithms including k-nearest neighbor (KNN), multilayer perceptron (MLP), and support vector machine (SVM) for brightness and contrast adjustment.
  • Compared F1 scores of edge detection on non-treated, pre-processed, and machine-learned pre-processed images.

Main Results:

  • The machine-learned pre-processed images achieved an average F1 score of 0.822 for edge detection.
  • This represents a 2.7-fold improvement compared to non-treated images.
  • The proposed method also facilitates clearer object determination for Auto White Balance (AWB) and Auto Exposure (AE) in ISPs.

Conclusions:

  • The proposed pre-processing and machine learning method is essential for optimizing images from ISPs for superior edge detection.
  • This approach enhances the efficiency and accuracy of image processing tasks within ISPs, including AWB and AE.