Shape Feature Extraction of High Resolution Remote Sensing Image Based on SUSAN and Moment Invariant

Image feature extraction is the most important aspect of content-based image retrieval. This paper presents a method for shape-based feature extraction of high resolution remote sensing image. Firstly the edges in the original image are detected according to Smallest Univalue Segment Assimilating Nucleus (SUSAN) principle. Then, the moment invariants of the edge map are calculated, and the result is used as the shape feature vector of the original image. Experimental results show that this method is simple and efficient, and the image feature can be well represented by this shape feature vector.