Akademik Veri Yönetim Sistemi
22nd IEEE Signal Processing and Communications Applications Conference (SIU), Trabzon, Türkiye, 23 - 25 Nisan 2014, ss.1067-1070
When image labeling (annotation) process for image retrieval is performed by fully automatic algorithms, labels have noise, errors and missing labels. Correcting labels gathered automatically from web (using information around an image such as text, user-tags, etc) is done manually using human labor. Therefore, coordination of different indivuduals is necessary for a consistent annotation. In this paper, a semiautomatic annotation tool designed with Matlab GUI has been proposed for an efficient and consistent image labeling. In the proposed framework, we first compare visual features of the query image and the labeled gallery images by using "Chi-Squared" distance. Then we create an ordered label list by using the labels of the closest images. The user finally selects the appropriate labels from the list and finishes the labeling process. The tool also allows one to enter new labels in case the returned labels are not enough to describe the image content. In this way the subjectivity of human perception and loss of time are reduced as well as consistency and coordination among different indivuduals' annotations are accomplished.