KEYWORDS: Hyperspectral imaging, Reflectivity, Detection and tracking algorithms, Data processing, Principal component analysis, Data modeling, Performance modeling
The storage conditions for paper cultural relics entail strict requisites. Any alterations to the storage conditions can lead to the proliferation of diseases, with mould being particularly prevalent and causing discoloured splotches on the surface of the relics. The resultant physical and biological damage is severe. In this study, we examine the differences in spectral characteristics between moldy and healthy areas in paper cultural relics samples. We used hyperspectral imaging technology, known for its non-destructive and fast features, to set up a discrimination model for phytophotocyanobacteria based on KNN (K-nearest neighbor), SVM(Support Vector Machine), 2D-CNN and VVG16, and evaluated the performance of the model by comparing the mold identification rate between different models to screen the optimal modelling scheme. The primary contributions of this paper are the amalgamation of hyperspectral imaging technology with mold spot detection of cultural relics on paper.
In order to achieve online non-destructive testing of mold growth and detection on wooden cultural relics, this paper proposes a reflective fiber optic sensor composed of one transmitting fiber and six inclined receiving fibers. The sensor is used to conduct experimental research on the growth of Trichoderma longibrachiatum and Cladosporium cultivated on wooden samples, and the relationship between the spectral information, absorbance, and growth height of the two molds is obtained. The experimental results indicate that the sensor can identify and accurately measure mold on the surface of wooden cultural relics, and the proposed sensor has good application prospects in the field of cultural relic detection.
KEYWORDS: Data modeling, Performance modeling, Evolutionary algorithms, Neural networks, Principal component analysis, Data processing, Spectral data processing, Education and training, Machine learning, Tunable filters
Paper cultural relics are important carriers of splendid history and culture, and have important historical research value. As paper is mainly rich in cellulose, starch and protein, paper cultural relics are prone to mould, insects and other microorganisms in the process of long-term preservation, leading to corrosion, deterioration and even destruction of cultural relics. Fumigation method is currently more widely used in a rapid means of control of cultural relics of mould and mildew, fumigant residue detection is the establishment of a set of scientific fumigation method in an indispensable part. In this paper, for the surface of paper cultural relics there are fumigant residues and no residues of spectral characteristics of the variability, based on the characteristics of spectral nondestructive testing, using BP neural network algorithm, SVM algorithm, KNN algorithm, 1D-CNN algorithm were established to establish discriminatory models, according to the different models of the discrimination accuracy of the model performance assessment, select the optimal modelling method.
In order to obtain the characteristics of orange penicillium growth on the surface of paper cultural relics, a reflective concave stepped oblique lens fiber optic sensor was developed. And in order to be more in line with the characteristics of paper artefacts, the paper artefacts were subjected to ink dyeing treatment. The sensor was used to monitor and analyse the growth process of Penicillium oryzae on the surface of ink-dyed cotton paper samples and burlap samples, and the structure and height of Penicillium oryzae biofilm were characterized by super depth-of-field microscope. The study shows that the sensor can accurately measure the biofilm height of the growth information of Penicillium oryzae on the surface of ink-dyed paper samples, and the output signal of the sensor has a linear relationship with the biofilm height of Penicillium oryzae.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.