Font Size: a A A

Animation Image Registration And Luster Removal Composition Technologyin Industry Assembly Line

Posted on:2011-01-04Degree:MasterType:Thesis
Country:ChinaCandidate:W H ZhuoFull Text:PDF
GTID:2178360308452344Subject:Pattern Recognition and Intelligent Systems
Abstract/Summary:PDF Full Text Request
Luster immediate influences the following algorithm performance in the field of Industry Detection,Pattern Recognition and Computer Vision. It is always the hot topic that how to detect and eliminate the luster region in the image.As we know, the existing Luster removal technology is mainly based on single image. But it is very difficult for us to process single image to eliminate the luster region, and the result of processing single image to eliminate the luster region is not so good. This article introduces a solution that Luster removal image composition technology based on continual frame image registration, and this solution is mainly concerning the supplementary information between the continual frame images. This solution is mainly including two parts: Image registration and Image fusion.First, we register the animation images by the way of feature detection and feature description or other image registration methods. Second, we fuse the registered images after matchingLast, we output the luster–removed image.This article mainly introduces a image registration method based on SURF in the Image registration module. This method is good at processing the most of images, but this method is not good at the image which contains few textural property. So, we propose a method which we called All Principal Edge Matching based on Canny. We can complete continual frame image registration by using these two image registration methods, and the final step is fusing the registered continual frame images. The experiment indicates that this method is good for eliminating the luster, and this solution has certain value in the field of theory and application.
Keywords/Search Tags:luster-removal, image registration, image fusing, SURF registr-ation, All principal line
PDF Full Text Request
Related items