基于汉字笔画特征的文本图像倒置判断算法  

A Judgment Algorithm for Inverted Chinese Text Image Based on Characteristics of Stroke

作　　者：王景中[1] 朱其猛 

机构地区：[1]北方工业大学信息工程学院,北京100144

出　　处：《计算机技术与发展》2014年第5期129-133,共5页Computer Technology and Development

基　　金："十一五"国家科技支撑平台重点项目(2009BA171B02);国家自然科学基金资助项目(61371142)

摘　　要：针对目前对文本图像倒置判断过分依赖文本标点的局限以及判断准确率不理想的问题,提出了一种新的中文文本图像倒置判断算法。算法运用投影法,对汉字进行定位,充分利用汉字笔画连续属性以及动态搜寻路径寻找撇笔迹,最后根据撇笔画的轮廓与走向特征运用特定的策略与算法判定出文本的方向。此法不仅很好地解决了上述问题,同时对扭曲的文本图像的倒置判断也有良好的效果。实验结果也验证了此法的可行性与有效性。通过实验结果与现有倒置判断算法相比,此法更具普遍适用性,在效率和准确率上也得到了较大的提高。Aiming at the problems of the judgment of inverted text image excessively relied on the punctuation and the text accuracy of judgment was not ideal,a new inversion judgment algorithm for Chinese text images is proposed. This algorithm makes full use of the outline of stroke and the characteristics of Chinese characters,on the basis of the left strokes founded by the software,using a particular al-gorithm to determine the direction of the text. The algorithm solves the problems above properly,at the same time,it has good effect for inversion judgment of distorted text image. The experimental results also verify the feasibility and effectiveness of this method. Compared with the existing inverted judgment algorithm,this method not only has more universal significance,efficiency and accuracy has also been largely increased.

关 键 词：文本定位 字符切分 笔画特征 撇笔迹 倒置判断 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]