A new multi-modal approach to bib number/text detection and recognition in Marathon images

作者：

Highlights：

• A new multi-modal approach to integrate torso and text detection for Marathon images.

• Upper body detection and segmentation by exploring SVM and Grab Cut.

• Texts in Marathon images are detected from torso results for assisting video analysis.

摘要

•A new multi-modal approach to integrate torso and text detection for Marathon images.•Upper body detection and segmentation by exploring SVM and Grab Cut.•Texts in Marathon images are detected from torso results for assisting video analysis.

论文关键词：Upper body detection,Grabcut segmentation,Torso detection,Text detection,Text recognition,Marathon images

论文评审过程：Received 17 July 2015, Revised 19 August 2016, Accepted 20 August 2016, Available online 22 August 2016, Version of Record 31 August 2016.

论文官网地址：https://doi.org/10.1016/j.patcog.2016.08.021