The existence of forgeries has seriously affected the fair trading, protection and inheritance of calligraphy and painting, while it has been unable to identify high-level counterfeiting means by traditional expert eye identification method. Combining the advantages of material attribute recognition and imaging analysis of hyperspectral imaging technology with the powerful feature expression and classification ability of convolutional neural network, the identification level of calligraphy and painting could be improved. However, there are still some practical problems in the application, like the small sample learning problem caused by the difficulty in obtaining the real hyperspectral sample data of calligraphy and painting. In this paper, a 10-hidden layers 2D-CNN convolutional neural network transfer learning method for calligraphy and painting identification with data enhancement is proposed by using a large number of relevant picture data and a small amount of MNF dimensionality reduced hyperspectral data. The experimental test shows that on the test set of this paper, for the identification of calligraphy and painting authors and authenticity, the accuracy of migration learning with data enhancement under the original sample are separately 97.5% and 94.8%, the accuracy of migration learning with data enhancement under half of the original sample are separately 94.3% and 92.8%, which shows the migration learning and data enhancement is helpful, and the identification accuracy of half of the original sample basically reaches the identification accuracy of the original sample without data enhancement and transfer learning, whose accuracy are 92.1% and 92.5%.
High radiation dose in CT imaging is a major concern, which could result in increased lifetime risk of cancers. Therefore, to reduce the radiation dose at the same time maintaining clinically acceptable CT image quality is desirable in CT application. One of the most successful strategies is to apply statistical iterative reconstruction (SIR) to obtain promising CT images at low dose. Although the SIR algorithms are effective, they usually have three disadvantages: 1) desired-image prior design; 2) optimal parameters selection; and 3) high computation burden. To address these three issues, in this work, inspired by the deep learning network for inverse problem, we present a low-dose CT image reconstruction strategy driven by a deep dual network (LdCT-Net) to yield high-quality CT images by incorporating both projection information and image information simultaneously. Specifically, the present LdCT-Net effectively reconstructs CT images by adequately taking into account the information learned in dual-domain, i.e., projection domain and image domain, simultaneously. The experiment results on patients data demonstrated the present LdCT-Net can achieve promising gains over other existing algorithms in terms of noise-induced artifacts suppression and edge details preservation.
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.