一种基于数字图像的碎纸拼接算法设计  

Algorithm Design on Scraps of Paper Splicing Based on Digital Image

作　　者：刘秋菊 王仲英[2] LIU Qiu-ju;WANG Zhong-ying(Information Engineering College,Zhengzhou Institute of Technology,Zhengzhou 450000,China;Engineering Economics College,Henan Institute of Economic and Trade,Zhengzhou 450018,China)

机构地区：[1]郑州工程技术学院信息工程学院,郑州450000 [2]河南经贸职业学院工程经济学院,郑州450018

出　　处：《科学技术与工程》2018年第29期222-225,共4页Science Technology and Engineering

基　　金：河南省科技攻关项目(172102210606);河南省高等学校重点科研项目(17B520040);郑州工程技术学院创新团队建设计划项目(CXTD2018K1)资助

摘　　要：提出了一种数字图像拼接复原的算法。首先利用BP神经网络对所有碎片进行归类;然后利用同一行的碎片特征必然非常相似这一特征作为依据,对分类后的碎片构造特征相似度函数,计算使相似性判别函数最大的单位矢量与碎片的特征矢量的距离,进行最大相似性判别,选出碎片间的差异最小的进行拼接。结合人工干预,最后得到拼接结果。实验结果表明该算法有效可行。An approach of recovery of digital image was proposed.First of all,all the pieces were classified by BP neural network,and then based on the feature that the characteristics of the same line must be very similar to construct the similarity function of the classified fragments,The distance between the largest unit vector of the similarity discriminant function and the feature vector is calculated to identify the maximum similarity.The minimum difference between the fragments is selected for stitching,combined with manual intervention,finally the stitching result is obtained.The results show that the method is effective and feasible.

关 键 词：数字图像 碎片拼接 BP神经网络 特征相似度 特征矢量 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]