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 Videos

A modified SPIHT algorithm for image coding with a joint MSE and classification distortion measure.

Shaorong Chang1, Lawrence Carin

  • 1Department of Electrical and Computer Engineering, Duke University, Durham, NC 27708-0291, USA. chshrong@ee.duke.edu

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
|March 8, 2006
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

Gradient Importance Learning for Incomplete Observations.

... International Conference on Learning Representations·2026
Same author

Capturing Actionable Dynamics with Structured Latent Ordinary Differential Equations.

Proceedings of machine learning research·2025
Same author

Enabling Counterfactual Survival Analysis with Balanced Representations.

ACM CHIL 2021 : proceedings of the 2021 ACM Conference on Health, Inference, and Learning : April 8-9, 2021, Virtual Event. ACM Conference on Health, Inference, and Learning (2021 : Online)·2025
Same author

Detecting implicit biases of large language models with Bayesian hypothesis testing.

Scientific reports·2025
Same author

A machine learning algorithm improves the diagnostic accuracy of the histologic component of antibody mediated rejection (AMR-H) in cardiac transplant endomyocardial biopsies.

Cardiovascular pathology : the official journal of the Society for Cardiovascular Pathology·2024
Same author

A Preliminary Study Comparing the Performance of Thyroid Molecular Tests to a Deep Learning Algorithm in Predicting Malignancy in Indeterminate Thyroid Fine Needle Aspiration Biopsies.

Thyroid : official journal of the American Thyroid Association·2023
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 enhances image compression by prioritizing wavelet coefficients crucial for image recognition, improving classification accuracy at low bit rates. The modified Set Partitioning in Hierarchical Trees (SPIHT) algorithm balances compression efficiency with classification performance.

Area of Science:

  • Digital Image Processing
  • Machine Learning for Computer Vision
  • Signal Processing and Compression

Background:

  • The Set Partitioning in Hierarchical Trees (SPIHT) algorithm is a wavelet-based progressive image compression method.
  • Mean Squared Error (MSE) is a common distortion measure but poorly correlates with image recognition quality, especially at low bit rates.
  • Conventional SPIHT may de-prioritize low-amplitude wavelet coefficients vital for texture classification.

Purpose of the Study:

  • To improve image compression techniques for better image recognition quality at low bit rates.
  • To develop a modified SPIHT algorithm that considers classification error alongside MSE.
  • To autonomously estimate wavelet subband importance for texture discrimination.

Main Methods:

Related Experiment Videos

  • Utilized Kernel Matching Pursuits (KMP) to assess the importance of wavelet subbands for distinguishing textures.
  • Employed a hidden Markov tree for initial textural segmentation.
  • Scaled wavelet coefficients based on KMP-derived subband importance before SPIHT coding.
  • Compared the modified SPIHT with original SPIHT and Bayes Tree-Structured Vector Quantization (B-TSVQ).

    • Main Results:

    • The modified SPIHT algorithm aims to minimize a Lagrangian distortion combining MSE and classification error.
    • This approach prioritizes wavelet coefficients important for distinguishing textures, enhancing classification accuracy.
    • Performance comparison demonstrated the effectiveness of the modified SPIHT against conventional SPIHT and B-TSVQ.

    Conclusions:

    • The proposed method effectively integrates image classification needs into the wavelet-based compression framework.
    • Prioritizing perceptually relevant coefficients improves recognition performance at reduced bit rates.
    • The modified SPIHT offers a superior tradeoff between compression efficiency and image recognition quality.