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

Downsampling01:20

Downsampling

183
When considering a sampled sequence with zero values between sampling instants, one can replace it by taking every N-th value of the sequence. At these integer multiples of N, the original and sampled sequences coincide. This process, known as decimation, involves extracting every N-th sample from a sequence, thereby creating a more efficient sequence.
The Fourier transform of the decimated sequence reveals a combination of scaled and shifted versions of the original spectrum. This...
183
Deconvolution01:20

Deconvolution

186
Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
186
Upsampling01:22

Upsampling

261
Managing signal sampling rates is essential in digital signal processing to maintain signal integrity. A decimated signal, characterized by a reduced frequency range due to its lower sampling rate, can be upsampled by inserting zeros between each sample. This upsampling process expands the original spectrum and introduces repeated spectral replicas at intervals dictated by the new Nyquist frequency. To refine this zero-inserted sequence, it is passed through a lowpass filter with a cutoff...
261
Fast Fourier Transform01:10

Fast Fourier Transform

376
The Fast Fourier Transform (FFT) is a computational algorithm designed to compute the Discrete Fourier Transform (DFT) efficiently. By breaking down the calculations into smaller, manageable sections, the FFT significantly reduces the computational complexity involved. Direct computation of an N-point DFT requires N2 complex multiplications, whereas the FFT algorithm needs only (N/2)log⁡2N multiplications, offering a much faster performance.
The computational efficiency of the FFT becomes...
376
Super-resolution Fluorescence Microscopy01:37

Super-resolution Fluorescence Microscopy

7.0K
Super-resolution fluorescence microscopy (SRFM) provides a better resolution than conventional fluorescence microscopy by reducing the point spread function (PSF). PSF is the light intensity distribution from a point that causes it to appear blurred. Due to PSF, each fluorescing point appears bigger than its actual size, and it is the PSF interference of nearby fluorophores that causes the blurred image. Various approaches to achieving higher resolution through SRFM have recently been...
7.0K
Discrete Fourier Transform01:15

Discrete Fourier Transform

320
The Discrete Fourier Transform (DFT) is a fundamental tool in signal processing, extending the discrete-time Fourier transform by evaluating discrete signals at uniformly spaced frequency intervals. This transformation converts a finite sequence of time-domain samples into frequency components, each representing complex sinusoids ordered by frequency. The DFT translates these sequences into the frequency domain, effectively indicating the magnitude and phase of each frequency component present...
320

You might also read

Related Articles

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

Sort by
Same author

Isolation, Antioxidant Activity, and Reaction Mechanism of Chamazulene from <i>Artemisia selengensis</i> Turcz. ex Besser Essential Oil.

ACS omega·2026
Same author

Correction: Metformin Improves the Impairment of Cognitive Function Caused by Total Abdominal Irradiation via the miR-34a-5p/BDNF/CREB Axis.

Molecular neurobiology·2026
Same author

Metformin improves the impairment of cognitive function caused by total abdominal irradiation via the miR-34a-5p/BDNF/CREB axis.

Molecular neurobiology·2026
Same author

Differential metabolic responses of mouse Leydig and spermatogonia cells to radiofrequency electromagnetic field exposure.

Frontiers in public health·2025
Same author

Fluorescent NH<sub>2</sub>-MIL-88(Fe)-stabilized PtNPs Nanozyme for Dual-Channel "OFF-ON" simultaneous and visual detection of glyphosate and Pb<sup>2+</sup> in Agri-environments and foodstuffs.

Food chemistry·2025
Same author

Dual-Mode Radiosensitization of Esophageal Squamous Cell Carcinoma via SOCS6-Loaded Virus-Inspired Manganese-Bismuth Bimetallic Oxide Nanoparticles.

Advanced healthcare materials·2025

Related Experiment Video

Updated: Jul 17, 2025

Lensless Fluorescent Microscopy on a Chip
11:23

Lensless Fluorescent Microscopy on a Chip

Published on: August 17, 2011

17.7K

Low-light image enhancement via adaptive frequency decomposition network.

Xiwen Liang1, Xiaoyan Chen2, Keying Ren1

  • 1School of Electronic Information and Automation, Tianjin University of Science and Technology, Tianjin, 300222, China.

Scientific Reports
|August 29, 2023
PubMed
Summary

This study introduces the Adaptive Frequency Decomposition Network (AFDNet) for enhancing low-light images. AFDNet improves visibility and detail by adaptively decomposing image frequencies, outperforming existing methods.

More Related Videos

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

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

Published on: December 15, 2023

568
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

441

Related Experiment Videos

Last Updated: Jul 17, 2025

Lensless Fluorescent Microscopy on a Chip
11:23

Lensless Fluorescent Microscopy on a Chip

Published on: August 17, 2011

17.7K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

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

Published on: December 15, 2023

568
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

441

Area of Science:

  • Computer Vision
  • Image Processing
  • Deep Learning

Background:

  • Low-light images suffer from poor visibility, noise, and blurred details.
  • Existing convolutional neural network (CNN) methods often amplify noise and blur details due to inadequate frequency information handling.

Purpose of the Study:

  • To develop a novel network, Adaptive Frequency Decomposition Network (AFDNet), for effective low-light image enhancement.
  • To address limitations in current CNN-based approaches by better utilizing image frequency characteristics.

Main Methods:

  • Proposed an Adaptive Frequency Decomposition (AFD) module to adaptively extract low and high frequency information at different granularities.
  • Employed low-frequency information for contrast enhancement and noise suppression, and high-frequency information for detail restoration.
  • Introduced a new frequency loss function to ensure robust recovery of different frequency components.

Main Results:

  • AFDNet demonstrated superior quantitative and visual performance compared to state-of-the-art methods on various datasets.
  • The network effectively enhances image visibility, restores details, and suppresses noise in low-light conditions.
  • Pre-processing images with AFDNet significantly improved the performance of face detection tasks.

Conclusions:

  • AFDNet offers an effective solution for low-light image enhancement by intelligently processing frequency information.
  • The proposed method overcomes limitations of existing techniques, providing better visual quality and detail restoration.
  • AFDNet has practical applications, enhancing subsequent computer vision tasks like face detection.