Authors:
Cheng-Chieh Chiang
1
;
Ming-Wei Hung
2
;
Yi-Ping Hung
2
and
Wee Kheng Leow
3
Affiliations:
1
Takming University of Science and Technology, Taiwan
;
2
Graduate Institute of Networking and Multimedia, National Taiwan University, Taiwan
;
3
School of Computing, National University of Singapore, Singapore
Keyword(s):
Image Annotation, Relevance Feedback, Semi-supervised Learning, Hierarchical Classifier.
Related
Ontology
Subjects/Areas/Topics:
Artificial Intelligence
;
Biomedical Engineering
;
Biomedical Signal Processing
;
Data Manipulation
;
Health Engineering and Technology Applications
;
Human-Computer Interaction
;
Methodologies and Methods
;
Neurocomputing
;
Neurotechnology, Electronics and Informatics
;
Pattern Recognition
;
Physiological Computing Systems
;
Sensor Networks
;
Soft Computing
Abstract:
This paper presents an approach for image annotation with relevance feedback that interactively employs a
semi-supervised learning to build hierarchical classifiers associated with annotation labels. We construct individual hierarchical classifiers each corresponding to one semantic label that is used for describing the semantic contents of the images. We adopt hierarchical approach for classifiers to divide the whole semantic concept associated with a label into several parts such that the complex contents in images can be simplified. We also design a
semi-supervised approach for learning classifiers reduces the need of training images by use of both labeled and unlabeled images. This proposed semi-supervised and hierarchical approach is involved in an interactive scheme of relevance feedbacks to assist the user in annotating images. Finally, we describe some experiments to show the performance of the proposed approach.