基于小波的ICM不变特征在图像匹配识别中的应用
Application of ICM Invariant Feature Based on Wavelet to Image Matching Recognition
-
摘要: 由于交叉皮层模型(intersecting cortical model,ICM)图标信号具有平移、旋转以及尺度不变性,因此,基于ICM的图像匹配算法能够提高实时目标图与基准目标图的匹配率,但根据ICM图标信号获取的不变特征对噪声信号较敏感。针对这一问题,提出了基于ICM和小波变换的图像匹配识别算法。仿真结果表明,本文算法在平移、尺度、旋转变化以及噪声环境下仍具有较高的匹配率。Abstract: Because ICM icon has the shift,scale and rotation invariance,so it is often used in image matching recognition algorithm to improve the matching rate of the real-time map and the reference map.But ICM icon is sensitive to the noise,so a novel recognition algorithm based on ICM icon and wavelet is introduced.The experimental results show that this method can gain high matching rate when the target has the shift,scale rotation change or noise.
下载:
