Hair detection, segmentation, and hairstyle classification in the wild

作者:

Highlights:

• A workflow performing complete hair analysis (detection, segmentation and hairstyle classification) from unconstrained view is proposed, using only texture information without employing any body-part classifiers.

• Figaro1k, a dataset of more than 1,000 unconstrained view images divided in seven hairstyle categories, is made publicly available along with the manually annotated hair masks.

• Achieved segmentation accuracy (beyond 90%) is above performance reached by known state-of-the-art algorithms.

• Automatic hairstyle recognition is performed for the first time by means of a multi-class texture classification step on the segmented hair region, obtained after the hair detection and segmentation phase.

摘要

•A workflow performing complete hair analysis (detection, segmentation and hairstyle classification) from unconstrained view is proposed, using only texture information without employing any body-part classifiers.•Figaro1k, a dataset of more than 1,000 unconstrained view images divided in seven hairstyle categories, is made publicly available along with the manually annotated hair masks.•Achieved segmentation accuracy (beyond 90%) is above performance reached by known state-of-the-art algorithms.•Automatic hairstyle recognition is performed for the first time by means of a multi-class texture classification step on the segmented hair region, obtained after the hair detection and segmentation phase.

论文关键词:Hair detection,Hair segmentation,Hairstyle classification,Texture analysis,Hair database

论文评审过程:Received 28 June 2017, Revised 22 January 2018, Accepted 4 February 2018, Available online 15 February 2018, Version of Record 24 February 2018.

论文官网地址:https://doi.org/10.1016/j.imavis.2018.02.001