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 Experiment Video

Updated: May 23, 2026

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments
03:31

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

Object detection with DoG scale-space: a multiple kernel learning approach.

Sharmin Nilufar, Nilanjan Ray, Hong Zhang

    IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
    |April 7, 2012
    PubMed
    Summary
    This summary is machine-generated.

    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

    Control of spiral breakup by an alternating advective field.

    The Journal of chemical physics·2006
    Same author

    Inhibition of growth and metastasis of human hepatocellular carcinoma by antisense oligonucleotide targeting signal transducer and activator of transcription 3.

    Clinical cancer research : an official journal of the American Association for Cancer Research·2006
    Same author

    New rod-plate anterior instrumentation for thoracolumbar/lumbar scoliosis: biomechanical evaluation compared with dual-rod and single-rod with structural interbody support.

    Spine·2006
    Same author

    Dimeric ansamycins--a new class of antitumor Hsp90 modulators with prolonged inhibitory activity.

    International journal of cancer·2006
    Same author

    A unified mode of epigenetic gene silencing: RNA meets polycomb group proteins.

    RNA biology·2006
    Same author

    Molecular signaling and genetic pathways of senescence: Its role in tumorigenesis and aging.

    Journal of cellular physiology·2006
    Same journal

    Change-Prior-Guided Unsupervised Change Detection of Heterogeneous Remote Sensing Images.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    Same journal

    AgonicDreamer: Enhancing Multi-View Consistency in Text-to-3D Generation via Rectified Score Distillation.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    Same journal

    BiCM-Prompt: Bidirectional Cross-Modal Prompt Tuning for Class-Incremental Learning on Multisource Remote Sensing Images.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    Same journal

    GoP-based Quality Enhancement on Video Compression.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    Same journal

    Align then Tensorize: Multi-Level Consistent Anchor Graph Learning for Scalable Multi-View Clustering.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    Same journal

    Beyond Fidelity: Diverse Image Synthesis via Retrieval-Augmented Diffusion.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    See all related articles

    This study introduces a multiple kernel learning (MKL) method to improve Difference of Gaussians (DoG) scale-space feature selection for object detection. The approach effectively handles high-dimensional data and selects optimal scales, outperforming existing methods.

    Area of Science:

    • Computer Vision
    • Machine Learning
    • Image Processing

    Background:

    • Difference of Gaussians (DoG) scale-space is crucial for image feature generation in object detection and classification.
    • Current methods face challenges with high-dimensional data and ad-hoc scale selection/weighting in DoG scale-space.
    • Automated and effective scale selection remains a significant challenge in image analysis.

    Purpose of the Study:

    • To propose a novel Multiple Kernel Learning (MKL) method for optimizing Difference of Gaussians (DoG) scale-space features.
    • To address the issues of high dimensionality and scale selection/weighting in DoG scale-space analysis.
    • To develop a data-dependent kernel that effectively utilizes discriminatory scales for object detection.

    Main Methods:

    • Developed a novel shift-invariant kernel function specifically for DoG scale-space.

    Related Experiment Videos

    Last Updated: May 23, 2026

    End-To-End Deep Neural Network for Salient Object Detection in Complex Environments
    03:31

    End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

    Published on: December 15, 2023

  • Implemented a Multiple Kernel Learning (MKL) framework utilizing a 1-norm Support Vector Machine (SVM) for sparse scale weighting.
  • Employed a 2-norm SVM with the learned kernel for applying the method to object detection tasks.

    • Main Results:

    • The proposed MKL method effectively selects and weights relevant scales from DoG scale-space, creating an optimized data-dependent kernel.
    • Successfully applied the learned kernel to detect large lumps in oil sand videos, a challenging industrial application.
    • Achieved encouraging results on difficult oil sand image datasets, demonstrating favorable comparison against other multiple kernel methods.

    Conclusions:

    • The novel MKL approach provides an effective solution for scale selection and weighting in DoG scale-space feature extraction.
    • This method offers a robust way to handle high-dimensional scale-space data, improving object detection performance.
    • The technique shows significant promise for challenging image analysis tasks, particularly in industrial settings like oil sand mining.