Research of a feature fusion model based on spatial equilibrium

When multiple features can affect your decision, how do you deal with this situation? Content-based image retrieval (CBIR), the selection of images from a collection via features extracted from images themselves, is a typical case of this problem. A simple but highly efficient model based on spatial equilibrium is presented to solve this problem in this paper. Three styles of model can meet the different scene of feature fusion need. The feature fusion model proposed in this paper can be effectively and efficiently used in CBIR. Experiments prove that the feature fusion method can combines multiple features for optimal retrieval reasonably and shown to be better than both the existing scoring approach and the existing ratio approach.