A Novel Approach for Automatic Image Annotation Using Enhanced Multi-Instance Differentiation Framework
T. Sumadhi, Mrs. S. Hemalatha · Procedia Engineering · 2012
Abstract With the rapid development of digital cameras, we have witnessed great interest and promise in automatic image annotation as a hot research field. Automatic image annotation is an effective method to resolve the problem of “Semantic Gap”. Automatic Image annotation is a challenging problem when a label is provided for the entire training image only instead of the object region. To eliminate labeling ambiguity, image categorization and object localization should be performed simultaneously. Discriminative Multiple Instance multi-label Learning (MIML) can be used for this task by regarding each image as a bag and sub-windows in the image as instances. Learning a discriminative Multi-instance classifier requires an iterative solution. In each round, positive sub-windows for the next round should be selected. With standard approaches, selecting only one positive sub-window per positive bag may limit the search space for global optimum; meanwhile, selecting all temporal positive sub-windows may add noise into learning. We select a subset of sub-windows per positive bag to avoid those limitations. Our Proposed EMID algorithm is able to take the correlation among instances, correlation among labels, and correlation between instances and labels simultaneously, and provides a very rich representation and learning potential. Experimental results demonstrate that our approach outperforms previous discriminative MIML approaches and standard categorization approaches.