Abstract
A non-destructive identification method was developed here based on dropout deep belief network in multi-spectral data of ancient ceramic. A fractional differential algorithm was proposed to enhance the spectral details by making use of the difference between the first and second-order differential pre-process spectral data. An unsupervised multi-layer restricted Boltzmann machine (RBM) was employed to extract some high-level features during pre-training. Some weight and bias values trained by RBM were used to initialize a back propagation (BP) neural network. The RBM deep belief network was fine-tuned by the BP neural network to promote the initiative performance of network training, which helped to overcome local optimal limitation of the network due to the random initializing weight parameter. The dropout strategy has been put forward into the RBM network to solve the over-fitting of small sample spectral data. The experimental results show that the proposed method has excellent recognition performance of the ceramics by comparisons with some other ones.
Highlights
Sensors 2021, 21, 1318. https://As one of the great treasures of world cultural heritage, ancient ceramics has many kinds, all of them having rich cultural connotations and high scientific and technological research value for the study of human civilization history
The results show that fractional differential pretreatment is helpful to the discrimination of the ceramics
Random forest [19] is prone to cause over-fitting since the multi-spectral data obtained have obvious amplitude fluctuation anomaly, which is effectively solved by the developed pre-processing and the dropout deep belief network model
Summary
Sensors 2021, 21, 1318. https://As one of the great treasures of world cultural heritage, ancient ceramics has many kinds, all of them having rich cultural connotations and high scientific and technological research value for the study of human civilization history. Since there is no standard for the classification of ceramics, it is difficult for people to unify the fault source in the dating and the authenticity discrimination of ceramics [1]. To overcome the limitations of personal experience, a lot of research on ceramics has been done. X-ray diffraction, scanning electron microscopy, and spectral analysis were usually carried out to discriminate ceramics [2,3,4,5,6,7,8]. Another research area is based on the manufacturing process of ceramics, including firing temperature, raw material treatment, and glaze formula [9,10,11,12,13]. Some researchers have studied the differences in element composition and other related information of ceramics from different origins and periods [14,15]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
