CAJ | 학술논문

图像拼接中,提高角点检测的精确度可以提高配准的精度.在Harris算法的基础上,提出了一种改进的角点检测算法,算法首先分别对图像中每行、每列上所有像素点的R_(Harris)进行X、Y方向的曲线拟合,然后对拟合后的曲线进行分析,若某个像素点的R_(Harris)值在两个方向上都处于"波峰"位置,则将该像素点检测为角点.实验结果表明该算法可以避免阈值的选择,有效地克服了阈值选择不当造成的角点冗余或丢失,提高了角点检测的精度.
도상병접중,제고각점검측적정학도가이제고배준적정도.재Harris산법적기출상,제출료일충개진적각점검측산법,산법수선분별대도상중매행、매렬상소유상소점적R_(Harris)진행X、Y방향적곡선의합,연후대의합후적곡선진행분석,약모개상소점적R_(Harris)치재량개방향상도처우"파봉"위치,칙장해상소점검측위각점.실험결과표명해산법가이피면역치적선택,유효지극복료역치선택불당조성적각점용여혹주실,제고료각점검측적정도.
Improving the precision of comer detection can get higher precision of image registration in image mosaics.An improved Harris-based corner detection algorithm is presented in the paper.It makes curve fitting to the R_(Harris) values of all pixels in every line on x-direction and every column on y-direction of the image respectively based on the Harris algorithm.And then, the curve is analyzed.When the R_(Harris) value of a certain pixel is at the wave peak position on both x and y direction,it is detected as a comer.The experiments show that this method can avoid corners redundancies or loss brought by unconnected threshold selection effectively and improve the precision of corners detection.