基于深度学习的草图分割算法综述
作者:
作者单位:

作者简介:

王佳欣(1993-),男,博士,主要研究领域为计算机视觉,深度视觉,图像分割;
马翠霞(1975-),女,博士,研究员,博士生导师,CCF高级会员,主要研究领域为人机交互,媒体大数据可视分析;
朱志亮(1988-),男,博士,讲师,CCF专业会员,主要研究领域为图像智能感知与增强,人机交互;
王宏安(1963-),男,博士,研究员,博士生导师,主要研究领域为自然人机交互,实时智能计算;
邓小明(1980-),男,博士,副研究员,CCF高级会员,主要研究领域为计算机视觉,人机交互.

通讯作者:

马翠霞,E-mail:cuixia@iscas.ac.cn

中图分类号:

基金项目:

国家自然科学基金(61872346);国家重点研发计划(2016YFB1001200)


Survey on Sketch Segmentation Algorithm Based on Deep Learning
Author:
Affiliation:

Fund Project:

National Key Research and Development Project (2016YFB1001200); National Natural Science Foundation of China (61872346)

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    草图一直是人类传递信息的重要工具之一.草图可以通过简单明了的形式更快地表达人类的一些复杂思想,因此,草图处理算法一直是计算机视觉领域的研究热点之一.目前,对草图的研究主要集中在识别、检索和补全等方面.随着研究者对于草图细粒度操作的重视,对草图分割方面的研究也得到越来越多的关注.近年来,随着深度学习与计算机视觉技术的发展,出现了大量基于深度学习的草图分割方法,草图分割的精确度和效率也都得到了较大提升.但是,由于草图自身的抽象性、稀疏性和多样性,草图分割仍然是一个非常具有挑战性的课题.对基于深度学习的草图分割算法进行整理、分类、分析和总结,首先阐述了3种基本的草图表示方法与常用的草图分割数据集,再按草图分割算法的预测结果分别介绍了草图语义分割、草图感知聚类与草图解析算法,然后在主要的数据集上收集与整理草图分割算法的评测结果并对结果进行分析,最后总结了草图分割相关的应用并探讨未来可能的发展方向.

    Abstract:

    Sketches have always been one of the important tools for human communication. As it can express some complex human thoughts quickly in a succinct form, the sketch processing algorithm is one of the research hotspots in the filed of computer vision. Currently, the research on sketches mainly focuses on the recognition, retrieval, and completion. As researchers focus on the fine-grained operation of sketches, research on sketch segmentation has also received more and more attention. In recent years, with the development of deep learning and computer vision technology, a large number of sketch segmentation methods based on deep learning have been proposed. Moreover, the accuracy and efficiency of sketch segmentation have also been significantly increased. Nevertheless, sketch segmentation is still a very challenging topic because of the abstraction, sparsity, and diversity of sketches. This study organizes, categorizes, analyzes, and summarizes the sketch segmentation algorithm based on deep learning to solve the above deficiency. Firstly, three basic sketch representation methods and commonly used sketch segmentation datasets are shown. According to the sketch segmentation algorithm prediction results, sketch semantic segmentation, sketch perceptual grouping, and sketch parsing are introduced respectively. Moreover, the evaluation results of sketch segmentation are collected and analyzed on the primary data sets. Finally, the application of sketch segmentation is summarized and the possible future development direction is discussed.

    参考文献
    相似文献
    引证文献
引用本文

王佳欣,朱志亮,邓小明,马翠霞,王宏安.基于深度学习的草图分割算法综述.软件学报,2022,33(7):2729-2752

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2020-08-07
  • 最后修改日期:2020-10-13
  • 录用日期:
  • 在线发布日期: 2021-01-15
  • 出版日期: 2022-07-25
您是第位访问者
版权所有:中国科学院软件研究所 京ICP备05046678号-3
地址:北京市海淀区中关村南四街4号,邮政编码:100190
电话:010-62562563 传真:010-62562533 Email:jos@iscas.ac.cn
技术支持:北京勤云科技发展有限公司

京公网安备 11040202500063号