王梦迪,张友梅,常发亮.基于边缘检测和特征融合的自然场景文本定位[J].计算机科学,2017,44(9):300-303, 314
基于边缘检测和特征融合的自然场景文本定位
Text Localization Based on Edge Detection and Features Fusion in Natural Scene
投稿时间:2016-08-26  修订日期:2016-11-04
DOI:10.11896/j.issn.1002-137X.2017.09.056
中文关键词:  自然场景,文本定位,边缘检测,特征融合
英文关键词:Natural scene,Text localization,Edge detection,Feature fusion
基金项目:本文受国家自然科学基金项目(61673244),高等学校博士学科点专项科研基金资助
作者单位E-mail
王梦迪 山东大学控制科学与工程学院 济南250061 wang_mengdi@yeah.net 
张友梅 山东大学控制科学与工程学院 济南250061  
常发亮 山东大学控制科学与工程学院 济南250061  
摘要点击次数: 239
全文下载次数: 137
中文摘要:
      文本定位作为文本识别的基础和前提,对图像深层信息的理解至关重要。针对自然场景下的文本定位受光照、复杂背景等因素影响较大的问题,提出了一种基于多方向边缘检测和自适应特征融合的自然场景文本定位方法。该方法首先将自然场景图像进行三通道八方向的边缘检测;然后 通过启发式规则 对得到的边缘图像进行过滤从而提取出备选文本域,进而对备选文本域进行自适应权值的HOG-LBP特征提取与融合;最后采用支持向量机进行特征分类学习,实现文本定位。实验结果表明,该方法能准确定位自然场景图片的文本区域,对光照和复杂背景具有较强的鲁棒性。
英文摘要:
      As the basis and premise of text recognition,text localization has an important influence on the analysis of images.Since the text localization in natural scene can be effected by illumination and the complex backgrounds significantly,we proposed a text localization method based on edge detection and features fusion.The method began with edge detection from three channels and eight directions,and then we filtered the detected edge images with heuristic rules to extract candidate text regions.On top of that,the HOG-LBP features were extracted and fused by adaptive weights.Finally,we applied support vector machine (SVM) to classify the candidate regions and realized text localization.Experimental results indicate that the proposed method can locate the text region accurately in natural scene images while reducing the influence of illumination and complex backgrounds effectively.
查看全文  查看/发表评论  下载PDF阅读器