Extracting spatial semantics in association rules for weather forecasting image

Association rule mining is one of the most important problems in image mining. We propose a new approach to apply association rule on weather forecasting image. We build an image system to store weather forecasting images and retrieve them later for further research, for example, to predict future temperature, relative humidity, rainfall, wind speed and atmospheric pressure. Image retrieval technology is therefore important. We describe weather forecasting image retrieval system based on content-based image retrieval. Currently, content based image retrieval technology does not exploit highlevel semantics, and it is hard to obtain predictive information from retrieved images. Association rules mining is applied in the search for these weather forecasting images. Most traditional data mining models focus on mining association rules among attributes within one transaction. Our improvement involves a spatial reference method that is used to get the spatial relationships between objects for a certain image. Spatial association rules are also mined and are subsequently used as a basis for retrieving additional images. As the spatial semantics in both the query image and spatial association rules retrieved images are more accurate. The proposed intelligent image retrieval system can get more images to help user predict future on weather forecasting.