WCSE

Border Image Generation Based on Residual Map Vote

Abstract— In this paper, a new algorithm is proposed to automatically generate border image for paint color game. First of all, region grow algorithm is applied. And then morphological closing operation is used to smooth every separated region. All regions are then labeled and the un-labeled regions form residual map. We then use vote strategy to decide the label of residual pixels. The final border image will be generated until no residual pixel exists. The experiments show that the proposed algorithm is robust and effective to produce border image for paint color game.

Index Terms— Image segmentation, Paint by number, paint color game

Shuchang Xu
College of Information Science and Engineering, Hangzhou Normal University, CHINA
Yiwei Liu
Learnings.ai, CHINA

[Download]

Cite: Shuchang Xu, Yiwei Liu, "Border Image Generation Based on Residual Map Vote," Proceedings of 2019 the 9th International Workshop on Computer Science and Engineering, pp. 233-237, Hong Kong, 15-17 June, 2019.