首页|期刊简介|投稿指南|分类索引|刊文选读|订阅指南|资料|样刊邮寄查询|常见问题解答|联系我们
蔡改贫,刘占,汪龙,等. 基于形态学优化处理的标记符分水岭矿石图像分割[J]. 科学技术与工程, 2020, 20(23): 9497-9502.
caigaipin,liuzhan,wanglong,et al.Image segmentation of watershed ore based on morphological optimization[J].Science Technology and Engineering,2020,20(23):9497-9502.
基于形态学优化处理的标记符分水岭矿石图像分割
Image segmentation of watershed ore based on morphological optimization
投稿时间:2019-08-28  修订日期:2020-05-04
DOI:
中文关键词:  形态学  标记符 分水岭  结构元素 矿石分割
英文关键词:morphology  markers watershed  structural elements  ore segmentation
基金项目:(51464017);江西省教育厅科技重点项目(GJJ150618)。第一
           
作者单位
蔡改贫 江西理工大学
刘占 江西理工大学
汪龙 江西理工大学
张丹荣 江西理工大学
摘要点击次数: 98
全文下载次数: 48
中文摘要:
      针对不同形状、颜色的堆积矿石在图像采集时出现粘连重叠、边缘模糊等问题,本文提出一种形态学优化处理的标记符分水岭算法对矿石图像进行特征识别与边界分割。首先采用双边滤波进行去噪处理,然后通过Canny边缘检测算子梯度化,得到梯度幅值图像;其次是采用形态学优化处理,重构堆积矿石的几何特征信息,分割矿石颗粒边缘;最后将图像进行可视化处理,获得彩色矿石颗粒分割图像。在形态学优化处理过程中,通过阈值分割数来寻找结构元素最佳参数,再通过分割率来确定最优结构元素。经实验和试验表明,该方法比传统标记符水岭算法分割更精准,且不同结构元素及其参数的变化对矿石分割效果影响较大,分割差异显著,当矩形结构元素长10,宽5时,其分割率最高,为95.68%,分割效果最佳。
英文摘要:
      In order to solve the problems of adhesion and overlap and edge blurring in the image collection of piled ore with different shapes and colors, a marker watershed algorithm based on morphological optimization is proposed in this paper to carry out feature recognition and boundary segmentation of ore images. Firstly, bilateral filtering was used for denoising, and Canny edge detection operator was gradient to get gradient image. Secondly, the morphological optimization is used to reconstruct the geometric feature information of the accumulated ore and to segment the grain edge of the ore. Finally, the image is visualized to obtain the color ore particle segmentation image. In the process of morphological optimization, the optimal parameters of structural elements are searched by threshold segmentation number, and the optimal structural elements are determined by segmentation rate. Experiments and experiments show that this method is more accurate than the traditional marker water-ridge algorithm, and the changes of different structural elements and their parameters have a great impact on the ore segmentation effect, with significant segmentation differences. When the rectangular structural elements are 10 long and 5 wide, the segmentation rate is the highest, 95.68%, and the segmentation effect is the best.
查看全文  查看/发表评论  下载PDF阅读器
关闭
你是第32690659位访问者
版权所有:科学技术与工程编辑部
主管:中国科学技术协会    主办:中国技术经济学会
Tel:(010)62118920 E-mail:stae@vip.163.com
京ICP备05035734号-4
技术支持:本系统由北京勤云科技发展有限公司设计

京公网安备 11010802029091号