Related Experiment Video
Updated: Jun 2, 2026

Three-Dimensional Shape Modeling and Analysis of Brain Structures
Published on: November 14, 2019
Revisiting complex moments for 2-D shape representation and image normalization
João B F P Crespo1, Pedro M Q Aguiar
1Institute for Systems and Robotics/Instituto Superior Técnico, Lisboa 1049-001, Portugal.
This study introduces Principal Moments for uniquely defining 2-D shape orientation, overcoming limitations of prior methods. Principal Moment Analysis offers a robust and efficient solution for shape normalization and image processing.
Area of Science:
- Computer Vision
- Image Processing
- Computational Geometry
Background:
- Normalization of 2-D shapes is crucial for comparison, with translation and scale easily handled.
- Defining and computing the orientation of general 2-D shapes remains a significant challenge.
- Existing methods fail to accurately compute orientation for simple shapes, even without noise.
Purpose of the Study:
- To uniquely define the orientation of arbitrary 2-D shapes.
- To develop a compact representation for 2-D shapes using Principal Moments.
- To introduce an efficient method for computing shape orientation and its application in image normalization.
Main Methods:
- Defining shape orientation using Principal Moments.
- Demonstrating that a subset of Principal Moments provides a compact shape representation.
- Proposing Principal Moment Analysis for efficient orientation computation.
- Exploring applications in gray-level image normalization.
Main Results:
- Successfully defined a unique orientation for arbitrary 2-D shapes.
- Showcased the compactness of Principal Moments for large-scale databases.
- Developed Principal Moment Analysis, an efficient method for shape orientation.
- Demonstrated robustness to noise and effectiveness on real images.
Conclusions:
- Principal Moments offer a novel and effective way to define 2-D shape orientation.
- Principal Moment Analysis provides an efficient and robust solution for shape normalization.
- The method has practical applications in processing real-world gray-level images.
More Related Videos
Related Concept Videos
Transformations of Functions II
Curvilinear Motion: Normal and Tangential Components
The positive direction of the t-axis aligns with the increasing position of the car along the curved path, denoted by the unit vector ut. Simultaneously, the n-axis, perpendicular to the t-axis, dissects the curved path into differential arc segments, each forming the arc of a circle with a radius of...
Moments of Inertia: Problem Solving
Support Reactions in Three Dimensions
Ball and Socket Joint is one of the supports allowing free rotation about any axis. This freedom of rotation is...
Curvilinear Motion: Rectangular Components
As the car advances, its position evolves over time. Quantifying the car's velocity involves computing the time...
Normal and Tangetial Components: Problem Solving

