Automated corrosion detection in Oddy test coupons using convolutional neural networks

Abstract

The Oddy test is an accelerated ageing test used to determine whether a material is appropriate for the storage, transport, or display of museum objects. The levels of corrosion seen on coupons of silver, copper, and lead indicate the material’s safety for use. Although the Oddy test is conducted in heritage institutions around the world, it is often critiqued for a lack of repeatability. Determining the level of corrosion is a manual and subjective process, in which outcomes are affected by differences in individuals’ perceptions and practices. This paper proposes that a more objective evaluation can be obtained by utilising a convolutional neural network (CNN) to locate the metal coupons and classify their corrosion levels. Images provided by the Metropolitan Museum of Art (the Met) were labelled for object detection and used to train a CNN. The CNN correctly identified the metal type and corrosion level of 98% of the coupons in a test set of the Met’s images. Images were also collected from the American Institute for Conservation’s Oddy test wiki page. These images suffered from low image quality and were missing the classification information needed to train the CNN. Experts from cultural heritage institutions evaluated the coupons in the images, but there was a high level of disagreement between expert classifications. Therefore, these images were not used to train the CNN. However, the images proved useful in testing the limitations of the CNN trained on the Met’s data when applied to images of coupons from different Oddy test protocols and photo documentation procedures. This paper presents the effectiveness of the CNN trained on the Met’s data to classify Met and non-Met Oddy test coupons. Finally, this paper proposes the next steps needed to produce a universal CNN-based classification tool. Graphic Abstract

Pollution and Heritage Metals—Effectiveness of Oddy Testing and Mitigation

“…Grazing angle is required for Ag [11] Raman All Analytical area often small, large numbers of measurements required for representative results [12] Fourier transform Infra-red spectroscopy (FTIR) Cu, Pb [13,14] Image capture and analysis Cu, Ag [8,15] Image analysis of photographs All [16,17] Mass Gain Cu, Pb Issues with different corrosion products providing different mass gains [18] Chemical stripping (mass loss) All [19] Potentiodynamic stripping (mass loss) Cu, Ag [20] Coulometric stripping (mass loss) Cu, Ag [21] Scanning electron microscopy (SEM) All [22] Table 1. Cont.…”

Electrochemical impedance spectroscopy evaluation of nonthermal plasma restoration for ductile metals in cultural heritage artifacts

“…In this sense, it is known that certain species of wood are very aggressive to lead because of the breakdown of cellulose compounds in the timber, and it produces volatile organic compounds (VOCs), especially acetic acid. [4,5] The effect of VOCs on lead corrosion is significant in the context not only of buildings but also in museums for the display of historic artifacts. The origin of this degradation is localized in the form of pitting corrosion and ends with the creation of a lead carbonate layer expanded through the surface.…”