RPTK1: A New Thangka Data Set for Object Detection of Thangka Images [PDF]
IEEE Access, 2021 Data set is the basis of machine learning, a good data set can promote the development of various applications. Machine learning has been deeply involved in the protection and inheritance of cultural resources.
Yuhong Chen, Zhen Fan, Xiaojing Liu
doaj +2 more sources
Thangka Image Captioning Based on Semantic Concept Prompt and Multimodal Feature Optimization [PDF]
Journal of Imaging, 2023 Thangka images exhibit a high level of diversity and richness, and the existing deep learning-based image captioning methods generate poor accuracy and richness of Chinese captions for Thangka images. To address this issue, this paper proposes a Semantic
Wenjin Hu +3 more
doaj +2 more sources
Thangka super-resolution diffusion model based on discrete cosine transform domain padding upsampling and high-frequency focused attention. [PDF]
PLoS ONEThangka is a traditional Tibetan painting art form, possessing profound cultural significance and a unique artistic style. Image super-resolution technology, as an effective means of digital preservation and restoration, plays an important role in ...
Xin Chen +5 more
doaj +3 more sources
Biocultural profiles of Qinghai Regong Thangka
Guangxi Zhiwu, 2023 The loss of biodiversity not only means the loss of genes, species and ecosystems, but also threatens the human cultural diversity. Thangka is known as the ‘encyclopaedia’ of traditional Tibetan culture, covering social, historical, cultural, religious ...
Chen LIN, Zhuo CHENG, Chunlin LONG
doaj +2 more sources
MythPose: Enhanced Detection of Complex Poses in Thangka Figures [PDF]
SensorsThangka is a unique form of painting in Tibet, which holds rich cultural significance and artistic value. In Thangkas, in addition to the standard human form, there are also figures with multiple limbs. Existing human pose estimation methods are not well
Yukai Xian +5 more
doaj +2 more sources
Artificial Intelligence for Pigment Classification Task in the Short-Wave Infrared Range [PDF]
Sensors, 2021 Hyperspectral reflectance imaging in the short-wave infrared range (SWIR, “extended NIR”, ca. 1000 to 2500 nm) has proven to provide enhanced characterization of paint materials.
Emeline Pouyet +3 more
doaj +2 more sources
Enhanced Object Detection in Thangka Images Using Gabor, Wavelet, and Color Feature Fusion [PDF]
SensorsThangka image detection poses unique challenges due to complex iconography, densely packed small-scale elements, and stylized color–texture compositions.
Yukai Xian +5 more
doaj +2 more sources
Visual symptoms associated with refractive errors among Thangka artists of Kathmandu valley [PDF]
BMC Ophthalmology, 2017 Background Prolong near work, especially among people with uncorrected refractive error is considered a potential source of visual symptoms. The present study aims to determine the visual symptoms and the association of those with refractive errors among
Deepa Dhungel, Gauri Shankar Shrestha
doaj +2 more sources
Multi-dimensional perception-guided iterative reflection removal network with deep features for painting images [PDF]
Scientific ReportsTo address the issue of image quality degradation caused by glass cover reflections during the digitization of Thangka paintings, this paper introduces an innovative iterative prediction network (MPGINet) guided by reflection perception and based on ...
Yuqi Xie, Xiaojuan Zhang, Yang Zhao
doaj +2 more sources
Особенности реставрации буддийских тангка
Искусство Евразии, 2021 Цель статьи — познакомить реставраторов и исследователей с традиционными и современными методами реставрации буддийской живописи на холсте, c оборудованием и материалами, которые применяются в лаборатории научной реставрации восточной живописи ...
Румянцева, В.А. +4 more
doaj +3 more sources