Full-Text Search:
Home|Journal Papers|About CNKI|User Service|FAQ|Contact Us|中文
《Journal of Chongqing University of Technology(Natural Science)》 2017-08
Add to Favorite Get Latest Update

Splicing Seam Elimination Method Based on Neighborhood Comparison

LUO Yongtao;ZHANG Hongmin;WANG Yan;ZHANG Jianshuang;CHEN Boyuan;College of Electrical and Electronic Engineering,Chongqing University of Technology;College of Computer Science and Engineering,Chongqing University of Technology;  
For finding splicing seam with low accuracy and it can't eliminate splicing seam effectively in the image splicing,a splicing seam elimination method based on neighborhood comparison is proposed. First of all,use a 3 × 3 sliding template to find a pixel point whose gray standard deviation value which is the largest in each row of number of rows continuously from the image overlap areas line by line,and to exclude the pixel points with large deviation until after two points in iteration,and tocalculate the mean value of the rest of points as the starting splice point of the splicing seam,and to set the threshold value to limit the range of candidate splicing point in turn on the basis of their column position. Then,it selects the points with largest gray standard deviation of the candidate points in the 3 × 3 neighborhood as the splice point of the row. Finally,it connects the optimal splicing point of each row as the optimal splicing seam. Experimental results show that the method can make the gray difference smaller on both sides of the splicing seam in order to eliminate the splicing seam relatively effectively,and to make the image overlap region smooth and natural,and to realize seamless splicing better.
【Fund】: 重庆市基础与前沿研究计划项目(cstc2015jcyj A40051)
【CateGory Index】: TP391.41
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
©2006 Tsinghua Tongfang Knowledge Network Technology Co., Ltd.(Beijing)(TTKN) All rights reserved