Author(s) :

Xinyun Zhang.

Volume/Issue :

Abstract :

Thangka has been a crucial aspect of Buddhism for thousands of years. It acts as a visualization of the myths and legends that shaped Buddhism and attracted many devotees to worship. Furthermore, Thangka also serves as a reflection of the cultural, political and social aspect of Tibetan society in history. However the paintings, especially the outlines, became extremely fragile after years of harsh environments. We utilized Deep learning, specifically the Convolutional neural network (CNN) as our main method for processing data. After numerous training the training loss gradually approaches 0, which means that the model no longer needs additional training. Under the CNN network we used max pooling which discards trivial information, rectified linear (ReLU) activation function, residential Network (ResNet), and other methods in our research to achieve a clear outline of Thangka. Through episodes of convolution and ReLU function, the image generated becomes gradually more defined in layer 1. However, as the image becomes processed continuously, it becomes gradually more abstract. Thus, the best results could be found in layer 1. Our study aims to use the results from the CNN network convolution to aid those who are studying the Thangka art in distinguishing the outlines of the image.