欢迎访问《图学学报》 分享到：
图学学报

图学学报

• 图像与视频处理 • 上一篇    下一篇

基于双层模型的宫廷服饰龙纹自动分割算法研究

  

  1. 1. 北京邮电大学数字媒体与设计艺术学院，北京 100876； 
    2. 北京邮电大学世纪学院移动媒体与文化计算北京市重点实验室，北京 102101
  • 出版日期:2019-02-28 发布日期:2019-02-27
  • 基金资助:
    国家自然科学基金项目(61163044)；北京市科委基金课题(D171100003717003)；甘肃省人才引进项目(2015-RC-47)

Automatic Segmentation of Dragon Design Based on Bi-Level Model in Chinese Imperial Costume Images

  1. 1. School of Digital Media & Design Arts, Beijing University of Posts and Telecommunication, Beijing 100876, China;  
    2. Beijing key Laboratory of Mobile Media and Cultural Computing, Beijing University of Posts and Telecommunications, Beijing 102101, China
  • Online:2019-02-28 Published:2019-02-27

PDF (PC)

130

摘要： 宫廷服饰纹样蕴含着丰富的文化内涵，但由于缺少像素级语义标注的数据库，使 得宫廷服饰纹样精准分割成为极具挑战的问题。为此，提出一种融合深度学习和 GrabCut 算法 的双层模型，实现目标检测和分割功能。分析不同深度卷积神经网络的特点，在模型目标检测 层(ODL)选择使用二阶段目标检测框架中的 R-FCN 方法；在模型分割层(SL)使用基于图论的 GrabCut 算法产生最终分割结果。在宫廷服饰图像数据集上进行仿真实验，证明基于深度卷积 神经网络和 GrabCut 算法的双层模型可以产生较好的分割效果。

关键词: 自动分割, 双层模型, 目标检测层, 分割层, 宫廷服饰图像

Abstract: The design pattern of Chinese imperial costumes contains rich cultural connotation. However, due to the lack of data set of pixel-level semantic annotation, the accurate segmentation of Chinese imperial costume images has become a very challenging problem. In this paper, a bi-level model integrating deep learning and GrabCut is proposed to realize the object detection and segmentation. The characteristics of different deep convolution neural network models are analyzed, and a two-stage object detector R-FCN is selected in the object detection layer (ODL). The segmentation layer (SL) of the proposed model employs GrabCut algorithm based on graph theory to produce final segmentation result. Experiments show that the proposed bi-level model can produce good segmentation results in the Chinese imperial costume image data set.

Key words:  automatic segmentation, bi-level model, object detection layer, segmentation layer, Chinese imperial costume image