Effective Image Mining by Representing Color Histograms as Time Series
Zaher Al Aghbari · Journal of Advanced Computational Intelligence and Intelligent Informatics · 2009
Due to the wide spread of digital libraries, digital cameras, and the increase access to WWW by individuals, the number of digital images that exist pose a great challenge. Easy access to such collections requires an index structure to facilitate random access to individual images and ease navigation of these images. As these images are not annotated or associated with descriptions, existing systems represent the images by their extracted low level features. In this paper, we demonstrate two image mining tasks, namely image classification and image clustering, which are preliminary steps in facilitating indexing and navigation. These tasks are based on the extraction of color distributions of images. Then, these color distributions are represented as time series. To make the representation more effective and efficient for the data mining tasks, we have chosen to represent the time series by a new representation called SAX (Symbolic Aggregate approXimation) [14]. SAX based representation is very effective because it reduces the dimensionality and lower bounds the distance measure. We demonstrate by our experiment the feasibility of our approach.