| 王小鹏,陈璐,吴双.基于面积约束和自适应梯度修正的分水岭图像分割[J].光电子激光,2014,(11):2219~2226 |
| 基于面积约束和自适应梯度修正的分水岭图像分割 |
| Watershed image segmentation based on area constraint and adaptive gradient modi fication |
| 投稿时间：2014-03-16 |
| DOI： |
| 中文关键词: 分水岭分割 面积约束 粘性形态学(VM)闭运算 梯度修正 |
| 英文关键词:watershed segmentation area constraint viscous morphological (VM) closing gra dient modification |
| 基金项目:国家自然科学基金(61261029)、甘肃省科技支撑计划(1204GKCA051)和金川公司预研基金(JC YY2013009)资助项目 (兰州交通大学 电子与信息工程学院, 甘肃 兰州 730070) |
|
| 摘要点击次数: 1628 |
| 全文下载次数: 182 |
| 中文摘要: |
| 图像中的噪声或非规则细节干扰易导致形态学 分水岭产生较严重的过分割,为了在消除过分割的同时尽可能 保持图像目标边界的准确定位,提出了一种基于面积约束和自适应梯度修正的分水岭图像分 割方法。首先对图像进行梯 度变换,采用区域面积约束滤除狭小高梯度尖峰对应的噪声和非规则细节；然后建立梯度级 与结构元素大小之间的函数 关系,并以相对应的结构元素对梯度图像进行粘性形态学(VM)闭运算,消除低梯度噪声及非 规则细节,实现梯度图像的自适 应修正,由于VM闭运算对梯度图像进行修正时,对目标仅作轻度或不作修正,因 而能够最大限度的保持目标轮 廓的准确定位,而对噪声和非规则细节则采用较大尺寸的结构元素进行较大幅度修正,从而 消除产生过分割的因素；最 后对修正图像进行分水岭分割。实验结果表明,本文方法能够在消除过分割的同时,保持目 标轮廓的准确定位。 |
| 英文摘要: |
| Morphological watershed segmentation often leads to a serious over-se gmentation due to the noises and irregular details within an image.Watershed segmentation based on area constraint and adap ti ve gradient modification is proposed to alleviate over-segmentation and boundary bias.Firstly,the original image is tra ns formed to a morphological gradient image.In gradient relief,the high gradient amplitudes with small area are usually corres ponding to salt-like noises or bright regular details, which can be removed by the area constraint.Secondly,the function between grad ient levels and morphological structure element is established,and the viscous morphological closing operator is utilized to mod ify the relief of gradient image with different sizes of structuring elements.The effects of viscous closing applied to objects and nois e are different.for the objects regions,the sizes of structuring elements are smaller,which means they are light or less modifica tion, while for noise or details,the larger size structuring elements are employed to modify them heavily.By such an adaptive mod ification,most irregular local minimums corresponding to the low amplitudes in gradient image caused by details and nois e w ill be removed,while positions of target boundaries have less change.Finally,standard watershed transform is employed to implement segmentation.Experiments show that this method can eliminate over-segmentation effectively while preserve th e location of object contours. |
| 查看全文 下载PDF阅读器 |
| 关闭 |
|
|
|
|
|