Automatic skin and hair masking using fully convolutional networks

Abstract

Selfies have become commonplace. More and more people take pictures of themselves, and enjoy enhancing these pictures using a variety of image processing techniques. One specific functionality of interest is automatic skin and hair segmentation, as this allows for processing one's skin and hair separately. Traditional approaches require user input in the form of fully specified trimaps, or at least of "scribbles" indicating foreground and background areas, with high-quality masks then generated via matting. Manual input, however, can be difficult or tedious, especially on a smartphone's small screen. In this paper, we propose the use of fully convolutional networks (FCN) and fully-connected CRF to perform pixel-level semantic segmentation into skin, hair and background. The trimap thus generated is given as input to a standard matting algorithm, resulting in accurate skin and hair alpha masks. Our method achieves state-of-the-art performance on the LFW Parts dataset [1]. The effectiveness of our method is also demonstrated with a specific application case.

Two-stage human hair segmentation in the wild using deep shape prior

“…Wang et al (2010Wang et al ( , 2012 decompose the hair segmentation into local parts and several other approaches (Wang et al, 2009(Wang et al, , 2011(Wang et al, , 2013 use region growing followed by refining regression on the coarse mask. Recent work (Chai et al, 2016;Qin et al, 2017;Guo and Aarabi, 2018;Levinshtein et al, 2017) based on FCNN models achieved good performance for practical applications. However, most of the methods only focus on constrained conditions such as head-shoulder images.…”

Effective Segmented Face Recognition (SFR) for IoT

“…In [22], the author proposed a method to achieve the segmentation of skin, hair, and background by applying FCN-8s and fully-connected CRF. Next, matting algorithm was facilitated in their experiment in order to receive clear hair and skin alpha masks.…”

Automatic Face and Hijab Segmentation using Convolutional Network

“…There are many deep learning approaches that are developed for different purposes, such as object detection, classification and segmentation. CNNs are the most commonly applied to image segmentation and classification [6]. Convolutional neural networks, Figure (2) Right, are a bit different where the layers are organized in three dimensions: width, height, and depth [19].…”