照度场中M阵列符号图像阈值分割方法研究  

Method of threshold segmentation for array of M noodle symbols graphic in illumination field

作　　者：鲁正[1] 喻擎苍[1] 胡恢军[1] 史明强[1] 

机构地区：[1]浙江理工大学信息电子学院,浙江杭州310018

出　　处：《计算机工程与设计》2012年第3期1047-1050,1056,共5页Computer Engineering and Design

基　　金：国家自然科学基金项目(50575211)

摘　　要：针对不均匀性照度场的干扰问题,从M阵列符号源图像阈值分割出发,摒弃前期研究中惯用的固定阈值分割方法,提出了以某一点为中心的邻域亮度和阈值对应的分布关系构建成该符号源图像的阈值分布场的自适应阈值分割方法,由此能得出在该照度场中的符号图像的合理阈值。实验结果表明,新的阈值分割方法可进一步提高符号的识别效率,并为后期的三维拼接工作奠定了良好的基础。Aiming at the problem of interference for uniform illumination field and starting from M noodle symbols graphic for threshold segmentation which discards of fixed threshold form professional study in prophase work. The self-adaptation threshold segmentation with relevance between with light intensity and threshold of some certain pix dot around is presented for threshold field forming of symbol graphic, and then the processing system can get reasonable threshold in illumination field. According to several experiment, new threshold segmentation can improve efficiency of symbol recognition more and bring practical utility in the upper work of three--dimensional combing and three-dimensional measure.

关 键 词：照度场 自适应 阈值分割 符号 识别 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]