Stroke-based sketched symbol reconstruction and segmentation

01/10/2019
by   Kurmanbek Kaiyrbekov, et al.
0

Hand-drawn objects usually consist of multiple semantically meaningful parts. For example, a stick figure consists of a head, a torso, and pairs of legs and arms. Efficient and accurate identification of these subparts promises to significantly improve algorithms for stylization, deformation, morphing and animation of 2D drawings. In this paper, we propose a neural network based model that segments symbols into stroke level components. Our segmentation network 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 the generative Variational Auto-Encoder (VAE) framework that draws symbols in stroke by stroke basis. Experiments show that a single encoder could be reused for segmenting multiple categories of sketches with negligible effects on segmentation accuracies. Extensive evaluations on our newly annotated dataset demonstrate that our model obtains significantly better scores as compared to the best baseline model. Moreover, our segmentation accuracies surpass existing methodologies on the available state of the art dataset. We also release our labeled dataset to the community.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/12/2016

Human Centred Object Co-Segmentation

Co-segmentation is the automatic extraction of the common semantic regio...
research
05/19/2017

VAE with a VampPrior

Many different methods to train deep generative models have been introdu...
research
06/06/2019

FSPool: Learning Set Representations with Featurewise Sort Pooling

We introduce a pooling method for sets of feature vectors based on sorti...
research
04/29/2020

An Auto-Encoder Strategy for Adaptive Image Segmentation

Deep neural networks are powerful tools for biomedical image segmentatio...
research
03/15/2022

CSN: Component-Supervised Network for Few-Shot Classification

The few-shot classification (FSC) task has been a hot research topic in ...
research
10/29/2021

NSS-VAEs: Generative Scene Decomposition for Visual Navigable Space Construction

Detecting navigable space is the first and also a critical step for succ...
research
06/30/2020

Hand-drawn Symbol Recognition of Surgical Flowsheet Graphs with Deep Image Segmentation

Perioperative data are essential to investigating the causes of adverse ...

Please sign up or login with your details

Forgot password? Click here to reset