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

Search research articles

Related Experiment Videos

Efficiently learning a detection cascade with sparse eigenvectors.

Chunhua Shen¹, Sakrapee Paisitkriangkrai, Jian Zhang

¹NICTA, Canberra Research Laboratory, Canberra, ACT 2601, Australia. chunhua.shen@nicta.com.au

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society

|July 6, 2010

Summary

This summary is machine-generated.

Related Concept Videos

Vector Algebra: Method of Components

Vector Algebra: Method of Components

It is cumbersome to find the magnitudes of vectors using the parallelogram rule or using the graphical method to perform mathematical operations like addition, subtraction, and multiplication. There are two ways to circumvent this algebraic complexity. One way is to draw the vectors to scale, as in navigation, and read approximate vector lengths and angles (directions) from the graphs. The other way is to use the method of components.
In many applications, the magnitudes and directions of...

You might also read

Related Articles

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

Sort by

Same author

Determination of non-volatile metabolic profiles and their sensory relevance in different grades of brandy through widely targeted metabolomics.

Food chemistry: X·2026

Same author

Atlas of predicted protein complex structures across kingdoms.

Nature communications·2026

Same author

The Clinical Utility of Whole-Exome Sequencing in the Prenatal Diagnosis of Fetal Skeletal Dysplasia.

International journal of women's health·2026

Same author

Accurate Industrial Anomaly Detection and Localization Using Weakly-Supervised Residual Transformers.

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

Same author

Study of Ultrasound Diagnosis of Acrania-Exencephaly-Anencephaly Sequence in Middle First Trimester: A Multicenter Center, Retrospective Analysis.

Journal of ultrasound in medicine : official journal of the American Institute of Ultrasound in Medicine·2025

Same author

Diffusion Models are Efficient Data Generators for Human Mesh Recovery.

IEEE transactions on pattern analysis and machine intelligence·2025

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

Feature selection methods beyond boosting, like greedy sparse linear discriminant analysis (GSLDA), can train efficient object detectors. Boosted GSLDA (BGSLDA) outperforms AdaBoost for real-time detection, especially with skewed data.

Area of Science:

Computer Vision
Machine Learning
Pattern Recognition

Background:

Real-time object detection is crucial for computer vision.
AdaBoost has been a dominant method since Viola and Jones's work.
Existing research focuses on improving boosting methods for object detection.

Purpose of the Study:

To demonstrate that feature selection methods, not just boosting, can train efficient object detectors.
To introduce Greedy Sparse Linear Discriminant Analysis (GSLDA) as a viable alternative.
To propose Boosted GSLDA (BGSLDA) for training efficient detection cascades.

Main Methods:

Introduced Greedy Sparse Linear Discriminant Analysis (GSLDA) for its simplicity and efficiency.
Developed Boosted GSLDA (BGSLDA) by combining boosting's sample reweighting with GSLDA's class-separability.

Related Experiment Videos

Conducted experiments on highly skewed data distributions, such as face detection.

Main Results:

GSLDA achieved slightly better detection performance compared to existing methods.
BGSLDA classifiers outperformed AdaBoost and its variants in experiments.
The proposed BGSLDA method efficiently trains detection cascades.

Conclusions:

Feature selection methods offer effective alternatives to boosting for object detection.
BGSLDA presents a novel and high-performing approach for real-time object detection.
AdaBoost is not the sole method for achieving high detection rates in real-time applications.