A Semantic Segmentation Model for Headdresses in Thangka Image Based on Line Drawing Augmentation and Spatial Prior Knowledge
Authors:
- 30 April 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 21 (22) , 25161-25170
Abstract
Thangka is a religious scroll painting. As a window to Tibetan traditional culture and religious customs, the segmentation of important semantic objects in the images can help the public understand the image content and realize high-level semantic cognition of the visual content. This paper proposes a semantic segmentation network for the central figures’ headdresses in the portrait-type Thangka images based on the rich structure and standard composition of Thangka images. Meanwhile, it has also constructed the first pixel-level semantic annotation data set of the central figures’ headdresses in Thangka images. Firstly, an original Thangka image witnesses edge augmentation through the line drawing augmentation module. Then the Feature Extraction Network is used to extract the feature map. After that, it uses the Half-RPN network to get the region of interest (ROI). Finally, Mask R-CNN Head completes segmentation and class prediction. The experimental results show that the performance of the proposed model is 10% to 19% better than that of the state-of-the-art models such as Mask R-CNN and DeepLab V3.Keywords
Funding Information
- the Nature Science Foundation of China (62061042, 61561042, 61862057)
- Fundamental Research Funds for the Central Universities (31920200066)
- Program for Innovative Research Team of State Ethnic Affairs Commission (2018 [98])
- Northwest Minzu University Graduate Research Innovation Project (Yxm2020106)
- Key Laboratory of China’s Ethnic Languages and Information Technology of Ministry of Education through the Special Fund for Talent Introduction of Northwestern Nationalities University
This publication has 13 references indexed in Scilit:
- Mask Scoring R-CNN2019
- Dual Attention Network for Scene Segmentation2019
- No reference quality assessment for Thangka color image based on superpixelJournal of Visual Communication and Image Representation, 2019
- Path Aggregation Network for Instance Segmentation2018
- Mask R-CNN2017
- Pyramid Scene Parsing Network2017
- DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- Deep Residual Learning for Image Recognition2016
- Fully convolutional networks for semantic segmentation2015
- Flow-Based Image AbstractionIEEE Transactions on Visualization and Computer Graphics, 2008