University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Toward Deep Universal Sketch Perceptual Grouper

Li, K., Pang, K., Song, Yi-Zhe, Xiang, T., Hospedales, T.M. and Zhang, H. (2019) Toward Deep Universal Sketch Perceptual Grouper IEEE Transactions on Image Processing, 28 (7). pp. 3219-3231.

Full text not available from this repository.

Abstract

Human free-hand sketches provide the useful data for studying human perceptual grouping, where the grouping principles such as the Gestalt laws of grouping are naturally in play during both the perception and sketching stages. In this paper, we make the first attempt to develop a universal sketch perceptual grouper. That is, a grouper that can be applied to sketches of any category created with any drawing style and ability, to group constituent strokes/segments into semantically meaningful object parts. The first obstacle to achieving this goal is the lack of large-scale datasets with grouping annotation. To overcome this, we contribute the largest sketch perceptual grouping dataset to date, consisting of 20 000 unique sketches evenly distributed over 25 object categories. Furthermore, we propose a novel deep perceptual grouping model learned with both generative and discriminative losses. The generative loss improves the generalization ability of the model, while the discriminative loss guarantees both local and global grouping consistency. Extensive experiments demonstrate that the proposed grouper significantly outperforms the state-of-the-art competitors. In addition, we show that our grouper is useful for a number of sketch analysis tasks, including sketch semantic segmentation, synthesis, and fine-grained sketch-based image retrieval. © 1992-2012 IEEE.

Item Type: Article
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering
Authors :
NameEmailORCID
Li, K.
Pang, K.
Song, Yi-Zhey.song@surrey.ac.uk
Xiang, T.
Hospedales, T.M.
Zhang, H.
Date : July 2019
DOI : 10.1109/TIP.2019.2895155
Copyright Disclaimer : No further action
Uncontrolled Keywords : Dataset; Deep grouping model; Sketch perceptual grouping; Universal grouper
Depositing User : Clive Harris
Date Deposited : 02 Jul 2019 08:22
Last Modified : 02 Jul 2019 08:22
URI: http://epubs.surrey.ac.uk/id/eprint/852101

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year


Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800