Automatic Image Annotation Using Color K-Means Clustering

Automatic image annotation is a process of modeling a human in assigning words to images based on visual observations. It is essential as manual annotation is time consuming especially for large databases and there is no standard captioning procedure because it is based on human perception. This paper discusses implementation of automatic image annotation using K-means clustering algorithm to annotate the colors with the appropriate words by using predefined colors. Experiments are conducted to identify the number of centroids, distance measures and initialization mode for the best clustering results. A prototype of an automatic image annotation is developed and then tested using thirty-five beach scenery photographs. Results showed that annotating image using evenly-spaced initialization mode and 100 centroids measured using City-Block distance function managed to achieve a commendable 75% precision rate.