图像特征提取算法仿真研究  

Improved Minimum Intensity Change Corner Extraction Algorithm

作　　者：马芳芳[1] 徐天乐[1] 

机构地区：[1]秦皇岛职业技术学院,河北秦皇岛066100

出　　处：《计算机仿真》2012年第8期227-229,304,共4页Computer Simulation

摘　　要：研究图像特征提取问题。针对传统的图像的角点检测算法由于算法复杂度较高,方法精度不高、速度较慢,同时易陷于局部最优等缺陷,而造成混淆图像的边缘点和角点,遗漏角点和角点的定位精确度低,提出用一种改进的最小亮度变化角点提取算法。首先采用最小亮度变化对图像的角点进行检测,然后在原有的算法的基础上加入角点预检测机制以及优化过滤机制,通过采用自适应阈值检测窗口,有效的滤除图像的伪角点,减少了噪声所带来的干扰,仿真结果表明,提出的改进的算法比传统MIC角点检测算法检测精确度大大提高,是一种有效的具有实际应用价值的图像角点检测算法。Research image corner detection extraction problem. The paper proposed an improved minimum brightness corner extraction algorithm. The minimum brightness variations were employed to detect image corner. Then based on the original algorithm, the corner detection mechanism and optimized filtering mechanism were joined. By using adaptive threshold detection window, the image comer was effectively filtered to reduce the noise caused by the interference. The simulation results show that the proposed algorithm is better than the traditional MIC corner de- tection algorithm. It greatly improves the accuracy and has practical application value.

关 键 词：角点检测 特征提取 最小亮度变化算法 阈值 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]