一种基于Gabor小波的超像素图像尺度空间特征提取算法  

A Scale Space Feature Extraction Algorithm for Superpixel Image Based on Gabor Wavelet

作　　者：卢金花 LU Jinhua(School of Information Management,Minnan University of Science and Technology,Shishi 362700,China)

机构地区：[1]闽南理工学院信息管理学院,福建石狮362700

出　　处：《西安文理学院学报(自然科学版)》2025年第1期8-12,共5页Journal of Xi’an University(Natural Science Edition)

基　　金：福建省中青年教师教育科研项目(科技类)(JAT220428)

摘　　要：为了对复杂图像数据进行高效表示和分析,提取有价值的图像特征信息,研究超像素图像尺度空间特征提取算法.使用一般滤波器构造出多级滤波器,使用多级滤波器抑制图像背景滤波,处理原始图像,对处理后的原始图像,进行超像素处理,以超像素为基元,分割图像,作为目标尺度空间,利用Gabor小波滤波器提取尺度空间特征,提取不受图像大小变化影响的尺度,为最佳尺度,计算特征值,提取对应的尺度空间特征.实验结果表明:基于Gabor小波的超像素图像尺度空间特征提取方法计算简单、速度快,特征值重复率不高,特征点提取效果较优.In order to efficiently represent and analyze complex image data and extract valuable image feature information,a superpixel image scale spatial feature extraction algorithm is proposed.Using a general filter,a multi-level filter is constructed to suppress image background filtering and process the original image.The processed original image undergoes superpixel processing,using superpixels as primitives,segmenting the image,and using Gabor wavelet filter to extract scale space features,extracting scales that are not affected by image size changes as the optimal scale,and calculating feature values,extracting corresponding scale space features.The experimental results show that the Gabor wavelet based method to extracting scale spatial features from superpixel images is computationally simple and fast,with a low repetition rate of feature values and favorable feature point extraction results.

关 键 词：GABOR小波 多级滤波器 特征提取 超像素处理 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]