An improved active shape model: Handling occlusion and outliers

Nicolae Duta; Milan Sonka

doi:10.1007/3-540-63507-6_225

Back

An improved active shape model: Handling occlusion and outliers

Book chapter

Open access

Peer reviewed

An improved active shape model: Handling occlusion and outliers

Nicolae Duta and Milan Sonka

Image Analysis and Processing, pp.398-405

Lecture Notes in Computer Science, Springer Berlin Heidelberg

07/30/2005

DOI: 10.1007/3-540-63507-6_225

Files and links (1)

url

https://doi.org/10.1007/3-540-63507-6_225View

Published (Version of record) Open Access

Abstract

An improvement of the Active Shape procedure identifying new examples of previously learned shapes using the point distribution model is presented. The novel segmentation and interpretation approach incorporates a priori knowledge about the objects of interest and their specific structural relationships to provide robust segmentation and labeling. The method was utilized to successfully identify 10 neuroanatomic structures in 19 individual MR images and 2 car classes (left-right and right-left oriented) in 400 perspective images of street scenes.

Active Shape Model

Outlier Detection

Outlier Removal

Perspective Image

Shape Model

Details

Title: Subtitle: An improved active shape model: Handling occlusion and outliers
Creators: Nicolae Duta - Michigan State University
Milan Sonka - University of Iowa
Resource Type: Book chapter
Publication Details: Image Analysis and Processing, pp.398-405
Series: Lecture Notes in Computer Science
DOI: 10.1007/3-540-63507-6_225
eISSN: 1611-3349
ISSN: 0302-9743
Publisher: Springer Berlin Heidelberg; Berlin, Heidelberg
Language: English
Date published: 07/30/2005
Academic Unit: Roy J. Carver Department of Biomedical Engineering; Electrical and Computer Engineering; Radiation Oncology; Fraternal Order of Eagles Diabetes Research Center; Injury Prevention Research Center; Ophthalmology and Visual Sciences
Record Identifier: 9984186708502771

Metrics

17 Record Views