摘要
针对图像检索系统提出了基于自适应阈值曲率增强的角点检测法,以及基于角点曲率的目标区域提取法.该算法将曲率作为角点重要程度的判断标准,通过自适应阈值判断图像的真伪角点,并增强真实角点的曲率信息,利用具有较大曲率的角点确定图像的重心,以重心为形心定位图像的目标区域.实验结果表明,本文算法不仅提高了图像角点检测的可靠性,而且有效地确定了其目标区域,最终达到了提高图像检索准确率以及算法运算效率的目的.为检索背景复杂的图像提供了新的思路和方法.
In image retrieval, comer detection with auto-adaptive threshold and target area extraction based on curvature are proposed in this paper. The algorithm judges the importance of comers by using curvature. Firstly, it selects the true comers through the auto-adaptive threshold. Meanwhile, they enhance their curvature. Then, it determines the image's center of gravity by the comers with larger curvature. Last, it extracts the target area by regarding the center of gravity as the centroid. The image retrieval experimental results show that this algorithm can not only detect the comers and extract the target area effectively, but also improve the accuracy and efficiency of image retrieval compared with the traditional method. It provides a new approach for the retrieval of image with complicated background.
出处
《计算机系统应用》
2015年第4期123-128,共6页
Computer Systems & Applications
基金
国家自然科学基金重点项目(61134009)
长江学者和创新团队发展计划(IRT1220)
上海领军人才专项资金
上海市科学技术委员会重点基础研究项目(13JC1407500
11JC1400200)
上海市教育委员会科研创新项目(14ZZ067)
中央高校基本科研业务费专项资金(2232012A3-04)
关键词
目标区域
角点
自适应阈值
曲率
图像检索
target area
comer
auto-adaptive threshold
curvature
image retrieval