Hand-drawn objects usually consist of multiple semantically meaningful parts. In this article, we propose a neural network model that segments sketched symbols into stroke-level components. Our segmentation framework has two main elements: a fixed feature extractor and a multilayer perceptron (MLP) network that identifies a component based on the feature. As the feature extractor we utilize an encoder of a stroke-rnn, which is our newly proposed generative variational auto-encoder (VAE) model that reconstructs symbols on a stroke-by-stroke basis. Experiments show that a single encoder could be reused for segmenting multiple categories of sketched symbols with negligible effects on segmentation accuracies. Our segmentation scores surpass existing methodologies on an available small state-of-the-art dataset. Moreover, extensive evaluations on our newly annotated big dataset demonstrate that our framework obtains significantly better accuracies as compared to baseline models. We release the dataset to the community.

中文翻译：

---

基于笔划的草图符号重建和分割

手绘对象通常由多个语义上有意义的部分组成。在本文中，我们提出了一种神经网络模型，可将草图符号分割为笔画级组件。我们的分割框架有两个主要元素：固定特征提取器和基于特征识别组件的多层感知器 (MLP) 网络。作为特征提取器，我们使用笔画-rnn 的编码器，这是我们新提出的生成变分自动编码器 (VAE) 模型，可在逐笔画的基础上重建符号。实验表明，单个编码器可以重复用于分割多个类别的草图符号，对分割精度的影响可以忽略不计。我们的分割分数在可用的小型最先进数据集上超过了现有方法。而且，对我们新注释的大数据集的广泛评估表明，与基线模型相比，我们的框架获得了明显更好的准确性。我们将数据集发布给社区。