A-contrario framework for detection of alterations in varnished surfaces

Abstract

Preventive conservation is the constant monitoring of the state of conservation of an artwork to reduce the risk of damages and so to minimize the necessity of restorations. Many methods have been proposed during time, generally including a mix of different analytical techniques. In this work, we present a probabilistic approach based on the a-contrario framework for the detection of alterations on varnished surfaces, in particular those of historical musical instruments. Our method is a one step Number of False Alarms (NFA) clustering solution which considers simultaneously gray-level and spatial density information in a single background model. The proposed approach is robust to noise and avoids parameter tuning as well as any assumption about the shape and size of the worn-out areas. Tests have been conducted on UV induced fluorescence (UVIFL) image sequences included in the “Violins UVIFL imagery” dataset. UVIFL photography is a well known diagnostic technique used to see details of a surface not perceivable with visible light. The obtained results prove the capability of the algorithm to properly detect the altered regions. Comparisons with other the state-of-the-art clustering methods show improvement in both precision and recall.