摘要
为了克服现有肖像唐卡图像头饰分割方法的局限性和像素级标注全监督语义分割的高成本,我们提出了一种带有框级标注的弱监督语义分割方法。首先,所提出的方法使用Canny算法来获取头饰的粗糙边缘。其次,利用改进的EDLines算法来提取头饰的关键点。最后,本文使用Polygons处理,根据头饰的特点生成特征掩码。实验表明,在人像唐卡图像佛像头饰的分割中,该方法的平均像素联合交集(mean intersection over union,mIoU)指数比语义分割实例方法(semantic segmentation instance,SDI)高7.56%,比弱监督实例分割-包围盒先验方法(weakly-supervised instance segmentation_bounding box prior,WSIS_BBTP)高6.11%,具有有效性。
In order to overcome the limitations of existing headdress segmentation methods in portrait Thangka images and the high cost of fully supervised semantic segmentation with pixel level annotation,we propose a weakly supervised semantic segmentation method with frame level annotation.Firstly,the proposed method uses Canny algorithm to obtain the rough edge of headdress.Secondly,the improved EDLines algorithm is used to extract the key points of headwear.Finally,we use Polygons processing to generate feature masks according to the characteristics of headwear.Experiments show that the mean intersection over union,mean intersection over union(mIoU)index of this method is 7.56%higher than semantic segmentation instance(SDI)and is 6.11%higher than weakly-supervised instance segmentation_bounding box prior(WSIS_BBTP).It is effective.
作者
王靖
齐延兴
WANG Jing;QI Yanxing(Department of Computer Science,Tangshan Normal University,Tangshan,Hebei 063000,China;School of Automation and Electrical Engineering,Linyi University,Linyi,Shandong 276005,China)
出处
《光电子．激光》
CAS
CSCD
北大核心
2022年第7期723-728,共6页
Journal of Optoelectronics·Laser
基金
唐山师范学院教育改革研究项目(2019JG014)资助项目
关键词
唐卡图像
语义分割
弱监督
Thangka image
semantic segmentation
weakly supervised
作者简介
齐延兴(1978-),男,硕士,讲师,主要研究方向为计算机控制与仿真、检测与控制等.E-mail:3633998690@qq.com
