Query-adaptive shape topic mining for hand-drawn sketch recognition
Query-adaptive shape topic mining for hand-drawn sketch recognition
复制标题
DOI：
10.1145/2393347.2393421
复制
发表时间：
2012-10
期刊：
影响因子：
--
通讯作者：
Zhenbang Sun;Changhu Wang;Liqing Zhang;Lei Zhang
中科院分区：
文献类型：
--
作者：
Zhenbang Sun;Changhu Wang;Liqing Zhang;Lei Zhang
在这项工作中，我们研究了手绘草图识别问题。由于手绘草图中存在大量的类内变化，大多数现有的工作仅限于特定的领域或有限的预定义类。不同于现有的工作，我们的目标是开发一个通用的草图识别系统，识别任何语义有意义的对象，儿童可以认识。为了提高识别覆盖率，利用网络规模的剪贴画图像集合作为识别系统的知识库。为了解决这种无约束情况下类内形状变化和类间形状模糊的问题，提出了一种查询自适应的形状主题模型来挖掘对象主题和与草图相关的形状主题，其中，草图、对象、形状、图像和语义标签等多个层次的信息在生成过程中被建模.除了草图识别，所提出的主题模型也可以用于相关的应用，如草图标记，图像标记，和基于草图的图像搜索。在不同应用中的大量实验表明了所提出的主题模型和识别系统的有效性。
In this work, we study the problem of hand-drawn sketch recognition. Due to large intra-class variations presented in hand-drawn sketches, most of existing work was limited to a particular domain or limited pre-defined classes. Different from existing work, we target at developing a general sketch recognition system, to recognize any semantically meaningful object that a child can recognize. To increase the recognition coverage, a web-scale clipart image collection is leveraged as the knowledge base of the recognition system. To alleviate the problems of intra-class shape variation and inter-class shape ambiguity in this unconstrained situation, a query-adaptive shape topic model is proposed to mine object topics and shape topics related to the sketch, in which, multiple layers of information such as sketch, object, shape, image, and semantic labels are modeled in a generative process. Besides sketch recognition, the proposed topic model can also be used for related applications such as sketch tagging, image tagging, and sketch-based image search. Extensive experiments on different applications show the effectiveness of the proposed topic model and the recognition system.