Model-based detection, segmentation, and classification for image analysis using on-line shape learning

Authors:
Kyoung-Mi Lee;W. Nick Street
Affiliations:
Center for Artificial Vision Research, Korea University, Seoul 136-701, Korea;Department of Managment Sciences, University of Iowa, Iowa City, IA
Venue:
Machine Vision and Applications
Year:
2003

Citing 9
Cited 4

Partial Shape Recognition: A Landmark-Based Approach

IEEE Transactions on Pattern Analysis and Machine Intelligence
Invariant Image Recognition by Zernike Moments

IEEE Transactions on Pattern Analysis and Machine Intelligence
A neural network approach to robust shape classification

Pattern Recognition
A shape recognition scheme based on relative distances of feature points from the centroid

Pattern Recognition
Vehicle Segmentation and Classification Using Deformable Templates

IEEE Transactions on Pattern Analysis and Machine Intelligence
Learning control strategies for object recognition

Symbolic visual learning
Generalizing over Aspect and Location for Rooftop Detection

WACV '98 Proceedings of the 4th IEEE Workshop on Applications of Computer Vision (WACV'98)
Human Shape Recognition from Snakes Using Neural Networks

ICCIMA '99 Proceedings of the 3rd International Conference on Computational Intelligence and Multimedia Applications
The use of the area under the ROC curve in the evaluation of machine learning algorithms

Pattern Recognition

Component-based face detection and verification

Pattern Recognition Letters
A shape-based voting algorithm for pedestrian detection and tracking

Pattern Recognition
Adaptive model-based multi-person tracking

CIS'04 Proceedings of the First international conference on Computational and Information Science
Component-based online learning for face detection and verification

CIS'05 Proceedings of the 2005 international conference on Computational Intelligence and Security - Volume Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

Detection, segmentation, and classification of specific objects are the key building blocks of a computer vision system for image analysis. This paper presents a unified model-based approach to these three tasks. It is based on using unsupervised learning to find a set of templates specific to the objects being outlined by the user. The templates are formed by averaging the shapes that belong to a particular cluster, and are used to guide a probabilistic search through the space of possible objects. The main difference from previously reported methods is the use of on-line learning, ideal for highly repetitive tasks. This results in faster and more accurate object detection, as system performance improves with continued use. Further, the information gained through clustering and user feedback is used to classify the objects for problems in which shape is relevant to the classification. The effectiveness of the resulting system is demonstrated in two applications: a medical diagnosis task using cytological images, and a vehicle recognition task.