计算机工程与设计
計算機工程與設計
계산궤공정여설계
Computer Engineering and Design
2015年
10期
2749-2753
,共5页
常旭剑%韩燮%熊风光
常旭劍%韓燮%熊風光
상욱검%한섭%웅풍광
局部特征%特征提取%特征描述%尺度不变转换特征%角点检测
跼部特徵%特徵提取%特徵描述%呎度不變轉換特徵%角點檢測
국부특정%특정제취%특정묘술%척도불변전환특정%각점검측
local feature%feature extraction%feature description%SIFT%corner detection
为快速、准确地实现图像局部特征提取,提高图像中目标识别的实时性,提出一种基于 FAST‐SIFT 组合的局部特征探测算法。使用FAST 检测算法进行快速的特征提取,利用SIFT 的128维描述子进行准确的特征描述,在匹配阶段采用基于SNR的朴素贝叶斯分类器,提高系统的鲁棒性。实验结果表明,与传统SIFT 算法相比较,该算法可以更快速地实现局部特征提取,在杂乱背景中能准确识别出目标物体。
為快速、準確地實現圖像跼部特徵提取,提高圖像中目標識彆的實時性,提齣一種基于 FAST‐SIFT 組閤的跼部特徵探測算法。使用FAST 檢測算法進行快速的特徵提取,利用SIFT 的128維描述子進行準確的特徵描述,在匹配階段採用基于SNR的樸素貝葉斯分類器,提高繫統的魯棒性。實驗結果錶明,與傳統SIFT 算法相比較,該算法可以更快速地實現跼部特徵提取,在雜亂揹景中能準確識彆齣目標物體。
위쾌속、준학지실현도상국부특정제취,제고도상중목표식별적실시성,제출일충기우 FAST‐SIFT 조합적국부특정탐측산법。사용FAST 검측산법진행쾌속적특정제취,이용SIFT 적128유묘술자진행준학적특정묘술,재필배계단채용기우SNR적박소패협사분류기,제고계통적로봉성。실험결과표명,여전통SIFT 산법상비교,해산법가이경쾌속지실현국부특정제취,재잡란배경중능준학식별출목표물체。
A local feature detection using FAST extraction combined with SIFT description was proposed to provide fast and ac‐curate local feature extraction and achieve real‐time object identification .FAST detection was applied for fast feature extraction , and a 128‐dimensional SIFT descriptor was created for each extracted feature .To increase robustness and eliminate outliers in matching ,signal to noise ratio (SNR) index that measured matched pairs’ spatial consistency was introduced .Object identity was inferred by propagating SNR through a naive Bayes classifier .Experimental results demonstrate the performance and speed of the proposed method are superior to traditional feature‐based approaches .