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

You might also read

Related Articles

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

Sort by

Same author

A framework based on hybrid Suzuki-Abe and convex Hull approach for improved classification of skin lesions.

Scientific reports·2026

Same author

LwHM: lightweight hybrid classifier for SDN-attack detection using recursive feature elimination.

Scientific reports·2026

Same author

Correction: An efficient Alzheimer's disease detection by NV classifier with BWTDL approach using MRI image.

BMC medical imaging·2026

Same author

XAI-MedNet: A Next-Generation Explainable AI Framework for Contrast-Enhanced Skin Lesion Classification via Entropy-Controlled Optimization.

Bioengineering (Basel, Switzerland)·2026

Same author

An Integrated Machine Learning and Genomic Framework for Precise Detection of Gastric Cancer.

The American journal of pathology·2026

Same author

Improving Deep Learning Based Lung Nodule Classification Through Optimized Adaptive Intensity Correction.

Bioengineering (Basel, Switzerland)·2026

Search research articles

Related Experiment Video

Updated: May 24, 2025

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

Efficient CNN architecture with image sensing and algorithmic channeling for dataset harmonization.

Khadija Kanwal^1,2, Khawaja Tehseen Ahmad³, Aiza Shabir⁴

¹School of computer science and technology, University of Science and Technology of China, Hefei, 230009, China. khadijakanwal@wum.edu.pk.

Scientific Reports

|March 4, 2025

Summary

This summary is machine-generated.

This study introduces a novel deep learning method for image analysis, integrating multiple neural networks to create efficient feature vectors. The approach enhances image recognition accuracy across diverse datasets and semantic categories.

Keywords:

Algorithmic channelizing Architectural bonding Composite structure Deep learning Features fusion

More Related Videos

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Published on: August 16, 2024

Related Experiment Videos

Last Updated: May 24, 2025

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

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Published on: August 16, 2024

Area of Science:

Computer Vision
Machine Learning
Deep Learning

Background:

Image formulation relies on semantic analysis for extracting influential vectors.
Existing methods face challenges in creating compact, efficient feature vectors adaptable to various datasets and semantic categories.

Purpose of the Study:

To develop an integrated deep learning approach for compact and efficient image feature vector extraction.
To enhance parallel data processing capabilities for images regardless of color consistency.
To improve the robustness and accuracy of image analysis across diverse datasets.

Main Methods:

Integration of DenseNet with ResNet-50, VGG-19, and GoogLeNet via algorithmic channeling.
Application of image patching techniques (corner straddling, isolated responses) for peak and junction detection.
Utilizing curvature-based computations and auto-correlation for noise reduction.
An integrated channeled algorithm for uniting local-global, primitive-parameterized, and regioned feature vectors.
Employing K-nearest neighbor indexing for efficient image retrieval.

Main Results:

Achieved compact and efficient image feature vectors.
Demonstrated parallel data processing irrespective of input color consistency.
Successfully addressed anisotropic noise and improved feature extraction.
Validated performance across multiple state-of-the-art datasets (Caltech-101, Cifar-10, Caltech-256, etc.).

Conclusions:

The proposed method achieves state-of-the-art deep image sensing analysis.
Delivers optimal channeling accuracy and robust dataset harmonization.
Establishes a new benchmark in complex image analysis and feature extraction.