Skin-based privacy filter for surveillance systems

With surveillance monitoring becoming widely available with the emergence of high resolution cameras, privacy concerns have been raised. One way to achieve privacy protection is by employing a privacy preserving device that can protect persons' identity, but still provide sufficient information to detect anomalous events if necessary. The skin region is important as a Personally Identifying Information (PII) that needs to be obscured if privacy is to be protected. Thus, this paper presents skin detection techniques to conceal privacy sensitive information. However, state-of-the-art skin detection methods suffer from various problems when deployed in a surveillance system. Accordingly, we propose a solution whereby we first find a set of candidate Regions-of-Interest (RoI) and then apply skin detection to the RoI thus found so as to locate the skin. By using this strategy, skin regions can be well delineated to allow targeted privacy filtering without covering the non-RoI parts.