Domain adaptation for holistic skin detection

Abstract

Human skin detection in images is a widely studied topic of Computer Vision for which it is commonly accepted that analysis of pixel color or local patches may suffice. This is because skin regions appear to be relatively uniform and many argue that there is a small chromatic variation among different samples. However, we found that there are strong biases in the datasets commonly used to train or tune skin detection methods. Furthermore, the lack of contextual information may hinder the performance of local approaches. In this paper we present a comprehensive evaluation of holistic and local Convolutional Neural Network (CNN) approaches on in-domain and cross-domain experiments and compare with state-of-theart pixel-based approaches. We also propose a combination of inductive transfer learning and unsupervised domain adaptation methods, which are evaluated on different domains under several amounts of labelled data availability. We show a clear superiority of CNN over pixel-based approaches even without labelled training samples on the target domain. Furthermore, we provide experimental support for the counter-intuitive superiority of holistic over local approaches for human skin detection.

A Standardized Approach for Skin Detection: Analysis of the Literature and Case Studies

“…This makes the comparison very difficult, due to the different testing protocols. For instance, recently, a research study compared different deep-learning approaching on different datasets, using different training sets [ 54 ]. In this work, we adopted a standard protocol to train the models and validate the results.…”

Weakly Supervised Human Skin Segmentation Using Guidance Attention Mechanisms

“…With the advent of deep learning, newer ideas have been proposed for human skin segmentation, many of which draw inspiration from the broader research area of semantic segmentation or a combination of various deep learning concepts. Early work treated the problem as a classification task by dividing an image into smaller patches and using deep networks to perform binary classification between skin and non-skin classes [37][38][39]. For example, Lei et al [38] proposed a patch-based skin segmentation method using stacked autoencoders to extract discriminative features from the blobs in an image, but this approach is not efficient in terms of time and resources required and it does not take into account relations between patches and contextual information.…”