This article summarizes the predecessor's research results and present situation in the field of image mosaic.It has discussed the core problem in the image mosaic algorithm, analyzed disadvantages of some algorithm.Simultaneously,it also summarized the development survey of Granular Computing theory and the its significance to the information subject,and introduced the principle of Granular Computing for the image mosaic technique. Based on this,it proposed a new feature-based image mosaic algorithm which take into account the accuracy and speed.Firstly,establish a granular computing model of the image and do the edge detection to obtain the image's edge segmentation;Secondly, extract the characteristic points in the edge graph use the information of gradient; Thirdly,carry on the related operation to these characteristic points to find matching characteristic points.The experimental result indicates that the algorithm in this article is a stable and steady method that superior than the traditional algorithm,and it gets well effectiveness.Innovation point of this article is trying to use the Granular Computing theory to realize the image mosaic,and provide a new mentality for the image mosaic technology. |