Perceptual-based region extraction from hand drawn sketches

Authors:
Rattapoom Waranusast
Affiliations:
Computer Science and Information Management Program, Asian Institute of Technology, Khlong Luang, Pathumthani,Thailand
Venue:
ACST'07 Proceedings of the third conference on IASTED International Conference: Advances in Computer Science and Technology
Year:
2007

Citing 6
Cited 0

Perceptual Organization for Scene Segmentation and Description

IEEE Transactions on Pattern Analysis and Machine Intelligence
Robust and Efficient Detection of Salient Convex Groups

IEEE Transactions on Pattern Analysis and Machine Intelligence
Supervised Learning of Large Perceptual Organization: Graph Spectral Partitioning and Learning Automata

IEEE Transactions on Pattern Analysis and Machine Intelligence
Finding Perceptually Closed Paths in Sketches and Drawings

IEEE Transactions on Pattern Analysis and Machine Intelligence
Perceptual organization in an interactive sketch editing application

ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
Sketch based interfaces: early processing for sketch understanding

Proceedings of the 2001 workshop on Perceptive user interfaces

Quantified Score

Hi-index	0.00

Visualization

Abstract

Pen-based computing devices have become more popular and more important, because it facilitates a natural way of input to users. To develop pen-based systems, automatic interpretation of sketches is crucial. However, this task is sensitive to drawing styles. This paper proposes a stroke grouping method based on Gestalt theory. The proposed algorithm group strokes into regions, each stroke is split into smaller stroke segments according to its corners and junctions. Then, for every stroke segments that can form closed loops, all possible regions are searched. Applying the notion of law of continuity in Gestalt theory to a set of all possible regions, scores of good continuity and convexity of all regions can be computed. The region with the best score is stored and extracted from the sketch. This iterative process is repeated until no stroke segments are left in the set of closed-loop segments. The algorithm implemented and tested on a tablet PC showed good results.