【作者】 王海禹； 黎宁； 李国强；

【Author】 Wang Haiyu Li Ning Li Guoqiang (College of Information Science and Technology, Nanjing University of Aeronautics and Astronautics. Nanjing. 210016)

【机构】 南京航空航天大学信息科学与技术学院；

【摘要】 本文提出一种新的基于灰度特征的图像分割方法,用于解决口服液药剂图像中杂质提取问题。首先,针对图像背景中存在的竖线与反光干扰,采用了纵向单列数据处理方式。其次,为了解决背景中灰度不均匀问题,给出了交叠式分块处理方法。最后,就图像中杂质边缘与背景灰度渐变问题,提出了基于均值阈值的分割算法,从而有效地提取出杂质区域。实验结果验证了该方法的有效性和实用性。更多还原

【Abstract】 A new image segmentation based on grey level is presented in this paper. The method is used to improve on exacting the impurity from oral medical liquid. First of all, fore-and-aft single rank processing way is to avoid interfere of vertical-line and glistening in practical images. Secondly, an over-lapped block method is provided for solving the diversification of illumination and the nonuniformity of grey. Finally, gradient-based segmentation is proposed to extract the impurity from the medical image. The experimental results have shown that the method have a powerful efficiency and practicability.更多还原