Thumbnail
Access Restriction
Open

Author Le, Cam-Tu Nguyen Ha Vu
Source CiteSeerX
Content type Text
File Format PDF
Subject Domain (in DDC) Computer science, information & general works ♦ Data processing & computer science
Subject Keyword Finer Level ♦ Cascade Manner ♦ Significant Improvement ♦ Weakly Labeling Problem ♦ Underlying Idea ♦ Learning Process ♦ Foreground Object ♦ Image Annotation ♦ Multi-level Multiinstance Classifier ♦ Background Label ♦ Baseline Method ♦ Coarse Level ♦ Automatic Image Annotation ♦ Proposed Scheme ♦ Negative Sample ♦ Cascade Algorithm ♦ Whole Image ♦ Important Negative Sample ♦ Ambiguous Background Label ♦ Useful Information ♦ Multi-level Feature Extraction ♦ New Scheme ♦ Multi-instance Learning ♦ Visual Feature Extraction ♦ Mil-based Method ♦ Weak Classifier
Abstract image annotation, cascade algorithm, multi-level feature extraction This paper introduces a new scheme for automatic image annotation based on cascading multi-level multiinstance classifiers (CMLMI). The proposed scheme employs a hierarchy for visual feature extraction, in which the feature set includes features extracted from the whole image at the coarsest level and from the overlapping sub-regions at finer levels. Multi-instance learning (MIL) is used to learn the “weak classifiers ” for these levels in a cascade manner. The underlying idea is that the coarse levels are suitable for background labels such as “forest ” and “city”, while finer levels bring useful information about foreground objects like “tiger” and “car”. The cascade manner allows this scheme to incorporate “important ” negative samples during the learning process, hence reducing the “weakly labeling ” problem by excluding ambiguous background labels associated with the negative samples. Experiments show that the CMLMI achieve significant improvements over baseline methods as well as existing MIL-based methods. 1
Educational Role Student ♦ Teacher
Age Range above 22 year
Educational Use Research
Education Level UG and PG ♦ Career/Technical Study
Learning Resource Type Article