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

A moment-based unified approach to image feature detection.

S Ghosal¹, R Mehrotra

¹Algorithm Res. Center, Sony Electron., Milpitas, CA.

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

|January 1, 1997

Summary

This study introduces a new model-based method for creating image feature maps, called primal sketches. This approach effectively extracts detailed feature information from images using Zernike moments for enhanced computer vision tasks.

Related Concept Videos

Difference from Background: Limit of Detection

Difference from Background: Limit of Detection

The limit of detection (LOD) is the smallest amount of analyte that can be distinguished from the background noise. The LOD value corresponds to the concentration at which the analyte signal is three times larger than the standard deviation of the blank signal. Below this value, the analyte signal cannot be differentiated from the background noise. It is calculated by dividing the calibration slope by 3 times the standard deviation of the blank signals.
The LOD indicates the presence or absence...

You might also read

Related Articles

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

Sort by

Same author

Effects of lifestyle and glucagon-like Peptide-1 receptor agonist-based therapies on waist circumference: A systematic review and meta-analysis.

Obesity pillars·2026

Same author

Combining phenotypic and genomic data to improve prediction of binary traits.

Journal of applied statistics·2024

Same author

Equitable inclusion of diverse populations in oncology clinical trials: deterrents and drivers.

ESMO open·2024

Same author

Packing a flexible fiber into a cavity.

Physical review. E·2022

Same author

Corrigendum to: Association of smokeless tobacco and cerebrovascular accident: a systematic review and meta-analysis of global data.

Journal of public health (Oxford, England)·2020

Same author

Exclusion-Enrichment Effect in Ionic Transistors.

Langmuir : the ACS journal of surfaces and colloids·2020

Area of Science:

Computer Vision
Image Processing
Pattern Recognition

Background:

Traditional image analysis often struggles with extracting comprehensive feature information.
High-level vision tasks require detailed understanding of image features beyond simple edge detection.

Purpose of the Study:

To propose a novel model-based approach for generating image feature maps (primal sketches).
To develop parametric models for characterizing local image intensity functions.
To identify moment-based detectors for extracting various primal sketches.

Main Methods:

A piecewise smooth parametric model is developed for local image intensity.
Orthogonal Zernike-moment-generating polynomials are used for parameter estimation.
Moment-based detectors are designed to extract primal sketches from intensity and range images.

Related Experiment Videos

Main Results:

The proposed method successfully generates feature maps by estimating model parameters.
A set of moment-based detectors is identified for diverse feature extraction.
The approach demonstrated effectiveness in extracting complete information about image features.

Conclusions:

Parametric model-based techniques offer a robust way to extract complete image feature information.
The developed feature detectors are effective for various computer vision applications.
This method enhances the capability of high-level vision tasks by providing detailed feature insights.