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

You might also read

Related Articles

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

Sort by
Same author

Smartwatch-Derived Digital Phenotypes Relate to Psychopathology Dimensions in Patients With Psychotic Spectrum Disorders: Longitudinal Observational Study.

JMIR mental health·2025
Same author

Revisiting Tropical Polynomial Division: Theory, Algorithms, and Application to Neural Networks.

IEEE transactions on neural networks and learning systems·2025
Same author

Time perception in film viewing: A modulation of scene's duration estimates as a function of film editing.

Acta psychologica·2024
Same author

Mushroom Detection and Three Dimensional Pose Estimation from Multi-View Point Clouds.

Sensors (Basel, Switzerland)·2023
Same author

Smartwatch digital phenotypes predict positive and negative symptom variation in a longitudinal monitoring study of patients with psychotic disorders.

Frontiers in psychiatry·2023
Same author

E-Prevention: Advanced Support System for Monitoring and Relapse Prevention in Patients with Psychotic Disorders Analyzing Long-Term Multimodal Data from Wearables and Video Captures.

Sensors (Basel, Switzerland)·2022
Same journal

Relation DETR+: Exploring Explicit Position Relation Prior for Dense Prediction.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

RBF++: Quantifying and Optimizing Reasoning Boundaries across Measurable and Unmeasurable Capabilities for Chain-of-Thought Reasoning.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

CAFE: Cross-View Adaptive Fusion and Cluster Center Enhancement for Robust Multi-View Clustering.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Driving.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Ethics-Aware Safe Reinforcement Learning for Rare-Event Risk Control in Interactive Urban Driving.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Learning Shape Anchors for Holistic Indoor Scene Understanding.

IEEE transactions on pattern analysis and machine intelligence·2026
See all related articles

Related Experiment Video

Updated: Jun 22, 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

Synergy between object recognition and image segmentation using the expectation-maximization algorithm.

Iasonas Kokkinos1, Petros Maragos

  • 1Department of Applied Mathematics, University of California, Los Angeles, CA, USA. iasonas.kokkinos@ecp.fr

IEEE Transactions on Pattern Analysis and Machine Intelligence
|June 23, 2009
PubMed
Summary
This summary is machine-generated.

This study integrates image segmentation and object recognition using the Expectation-Maximization algorithm. Active Appearance Models are employed for simultaneous image segmentation and object reconstruction, improving recognition accuracy.

More Related Videos

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data
12:08

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
04:48

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

Published on: November 30, 2022

Related Experiment Videos

Last Updated: Jun 22, 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

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data
12:08

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
04:48

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

Published on: November 30, 2022

Area of Science:

  • Computer Vision
  • Machine Learning
  • Image Analysis

Background:

  • Image segmentation and object recognition are fundamental computer vision tasks.
  • Integrating these tasks can improve overall performance and robustness.
  • Active Appearance Models (AAMs) are effective for modeling object shape and appearance variations.

Purpose of the Study:

  • To develop a unified framework for joint image segmentation and object recognition.
  • To leverage the Expectation-Maximization (EM) algorithm for this integrated approach.
  • To utilize AAMs for robust object modeling within the EM framework.

Main Methods:

  • Formulation of the interaction between segmentation and recognition within the EM algorithm framework.
  • Segmentation as the E-step (assigning observations to object hypotheses) and model fitting as the M-step.
  • Two novel top-down segmentation algorithms utilizing AAMs: one based on oversegmentation and soft assignment, another using curve evolution with AAMs as shape priors.

Main Results:

  • Simultaneous segmentation and reconstruction of images in terms of objects.
  • Derived AAM fitting equations that handle occlusions by incorporating segmentation information.
  • Experimental validation of the joint approach for object detection, demonstrating its advantages over separate methods.

Conclusions:

  • The proposed joint framework effectively integrates image segmentation and object recognition.
  • The use of AAMs within the EM algorithm enhances both segmentation and recognition tasks, including occlusion handling.
  • The approach offers a robust and automated solution for simultaneous image analysis and object identification.