Pattern segmentation based on PoolNet and boundary connectivity

Abstract

Traditional image segmentation algorithms need to design features manually. Therefore, based on the advantage of PoolNet in object detection, this paper proposes a clothing pattern segmentation algorithm combining PoolNet detection and boundary connectivity. This algorithm has more fine edges than traditional segmentation. Especially in the case of similar background before and after, we can get more complete pattern elements, and have better results in segmentation accuracy.

Keywords

• significance test
• boundary connectivity
• pattern segmentation
• poolnet