基于Gabor变换的凹凸字符图像特征抽取新方法  

Novel Feature Extraction Method for Raised or Indented Characters Based on Gabor Transform

作　　者：李建美[1] 路长厚[1] 李国平[2] 

机构地区：[1]山东大学机械工程学院,山东济南250061 [2]济南大学机械工程学院,山东济南250022

出　　处：《系统仿真学报》2008年第8期2133-2136,共4页Journal of System Simulation

基　　金：教育部博士基金资助项目(20060422011)

摘　　要：凹凸字符在成像时,由于字符和背景的材料和颜色一致,得到的图像对比度较低,在提取字符特征时较一般字符相比难度较大。针对此问题,根据标牌凹凸字符的特点,首次提出了一种基于灰度图像和Gabor变换的凹凸字符特征提取新方法。首先设计了一组Gabor滤波器,然后对凹凸字符的灰度图像直接进行特征抽取,分别提取凹凸字符水平、竖直、左、右对角线等四个方向上的局部笔画特征,在此基础上,继而建立一种不变Gabor特征空间,经大量实验证明这种不变Gabor特征具有优良的可分性,并且具有良好的旋转、尺度和平移不变性,同时对光照变化和噪声也具有较强的鲁棒性,从而进一步证明Gabor滤波器适宜于应用在低质量图像的特征提取中。Images of raised or indented characters are of poor contrast because the characters have the same color and material as the background. So the recognition of such characters is difficult than that of the conventional optical characters, To address this issue, a novel feature extraction method for raised or indented characters pressed on a label using Gabor transform was proposed. A set of Gabor filters was designed according to the characteristics of the raised or indented characters. These filters were used to break down a gray image of a character into four directional feature sub-images to get the local Gabor features. Based on these local features, an invariant feature space was established. Experiments were carried out with a large number of raised or indented character images. Experiment results show that the proposed invariant Gabor features have great separate capability and have great robust to rotation, scale, translation invariance and are also insensitive to illumination conditions and noise changes. It is proved that Gabor transform can be reliably used in low level feature extraction in image processing.

关 键 词：凹凸字符 GABOR变换 不变特征 灰度图像 字符识别 

分 类 号：TP391.43[自动化与计算机技术—计算机应用技术] TP751.1[自动化与计算机技术—计算机科学与技术]