CAJ | 학술논문

SIFT算法是性能最好、应用最广泛的基于局部特征的图像匹配算法,但其计算复杂度高.为此,提出一种SIFT和旋转不变LBP相结合的图像匹配算法,以提高SIFT算法的速度.首先利用SIFT关键点检测方法在2幅待匹配图像上分别检测关键点,得到2个关键点集;然后计算每个关键点周围图像区域的旋转不变LBP特征,并将其作为该关键点的描述;最后采用基于关键点最近邻距离比值的匹配策略,找出2个关键点集之间存在匹配关系的关键点对.实验结果表明,文中算法对结构内容图像的匹配性能与SIFT算法相当,运算速度比SIFT算法大为提高.
SIFT산법시성능최호、응용최엄범적기우국부특정적도상필배산법,단기계산복잡도고.위차,제출일충SIFT화선전불변LBP상결합적도상필배산법,이제고SIFT산법적속도.수선이용SIFT관건점검측방법재2폭대필배도상상분별검측관건점,득도2개관건점집;연후계산매개관건점주위도상구역적선전불변LBP특정,병장기작위해관건점적묘술;최후채용기우관건점최근린거리비치적필배책략,조출2개관건점집지간존재필배관계적관건점대.실험결과표명,문중산법대결구내용도상적필배성능여SIFT산법상당,운산속도비SIFT산법대위제고.
SIFT (scale invariant feature transform)is one of the most robust and the widely used image matching algorithms based on local features. However, its computational complexity is high. Aiming at speeding up the SIFT computation, we present an image matching algorithm by combining SIFT and the rotation-invariant LBP (local binary patterns). Firstly,two sets of keypoints are extracted from the two images for matching by applying the SIFT algorithm; Secondly, each keypoint is described by the rotation-invariant LBP patterns, which are computed from the image patch centered at the keypoint; Finally,the matching pairs between the two sets of keypoints are determined by using the nearest neighbor distance ratio based matching strategy. The experimental results show that the proposed SIFT+LBP algorithm is more rapid than the standard SIFT algorithm while the performance is favorably compared to the standard SIFT algorithm when matching among structured scene images.