| 形态学重度污染文本图像去噪处理 |
| |
| 引用本文： | 鄢煜尘,周前进,段柳云,陈庆虎.形态学重度污染文本图像去噪处理[J].武汉大学学报(信息科学版),2012,37(9):1100-1103. |
| |
| 作者姓名： | 鄢煜尘 周前进 段柳云 陈庆虎 |
| |
| 作者单位： | 武汉大学电子信息学院,武汉市珞珈山,430072 |
| |
| 基金项目： | 中国刑事警察学院文件检验鉴定公安部重点实验室资助项目 |
| |
| 摘 要： | 为处理扫描与复印图像产生的重度污染噪声,对噪声与文本信息的形态差异进行研究。利用灰度形态学原理,构建四方向形态学结构元素模版去除复杂的背影噪声,保留具有明显方向性的文字信息。针对噪声与文字在图像局部梯度上的特点,引入局部结构张量信息构造动态尺度的形态学结构元素,在可能的噪声区域采用较大尺度结构元素较好地滤除噪声,在可能含有文字的区域采用较小的结构元素以完整地保留易丢失的文字笔划与标点。最后利用灰度形态学重建恢复原始的文本内容,得到只含文本信息的图像。
|
| 关 键 词： | 图像去噪 形态学处理 动态尺度 局部结构张量 |
Morphologic Severely Polluted Documental Image Processing |
| |
| YAN Yuchen,ZHOU Qianjin,DUAN Liuyun,CHEN Qinghu.Morphologic Severely Polluted Documental Image Processing[J].Geomatics and Information Science of Wuhan University,2012,37(9):1100-1103. |
| |
| Authors: | YAN Yuchen ZHOU Qianjin DUAN Liuyun CHEN Qinghu |
| |
| Institution: | 1(1 School of Electronic Information,Wuhan University,Luojia Hill,Wuhan 430072,China) |
| |
| Abstract: | To denoise the severely polluted documental image produced by the process of scanning or duplicating,characteristics of noise and text content are investigated.Gray morphology with constructed four direction structuring elements is applied to filter the severely background noise and retain directional text content information.Local structural tensor is brought in to describe the local gradient difference between noise and text content,making the scale element dynamic,which will be larger when process probable noise area and smaller when it is closed to the text.By this way,denoising is satisfying and easily lost stroke and punctuation are well saved.Finally gray morphologic reconstruction is applied to recover original text content information,picking up image only containing text information.Comparing with normal image processing methods,this proposed approach has got efficient effect,which is suitable to deal with this kind of severely polluted documental image. |
| |
| Keywords: | image denoising morphologic processing dynamic scale local structural tensor |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
