一种基于火柴棒模型的图像水平倾斜矫正算法  

An approach to horizontal tilt correction based on matchstick model

作　　者：吴震宇[1] 杜宇人[1] 

机构地区：[1]扬州大学信息工程学院,江苏扬州225009

出　　处：《扬州大学学报（自然科学版）》2009年第4期66-69,共4页Journal of Yangzhou University：Natural Science Edition

基　　金：国家自然科学基金资助项目(20299030);扬州大学自然科学基金资助项目(KK0313090)

摘　　要：针对二值化图像中待识目标倾斜的问题,提出一种基于火柴棒模型的图像水平倾斜矫正算法.首先将原图像二值化,对该区域进行去噪处理,获取目标区域,然后构建"火柴棒"模型,再采用该模型对图像进行水平倾斜矫正.实验结果表明,该方法能有效克服目标区域较小、附近干扰较多、边缘不清晰等情况带来的不良影响,矫正效果良好.Since the identifying target area is tilt in binary images, an approach to horizontal tilt correction based on matehstiek model is presented. First, the original image is binarized and the ngise is removed to get the target area. Then the ＂matchstick model＂ is built up. This model is used to make horizontal tilt correction to the image. Experimental results show that this method is of great help in reducing those unfavorable influences caused by a relatively small target area, more interference and unsharp edges, etc. The result of correction is well.

关 键 词：图像分析 水平倾斜矫正 火柴棒模型 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]