
As an Amazon Associate and affiliate partner, Menrva Books earns from qualifying purchases. Learn more
Semantic description and annotation of digital images is the key to management and reusing of images in humanities computing. Due to the lack of domain-specific hierarchical description schema and controlled vocabulary for digital images, annotation results produced by current methods such as machine annotation based on low-level visual features of images, and human annotation based on expert's experiences,have the problem of low quality and inconsistency. To solve this problem,we propose a semantic description framework for the content description based on information needs and retrieval theory. The framework combines a semantic description framework and a domain thesaurus. In this paper, we elaborate on the relationship between semantic levels under this description framework. Then, we conduct a preliminary test with this method in the cultural heritage field using the Dunhuang fresco digital image. We discuss the effect of semantic granularity on the annotation cost from the point view of image semantic description granularity and control strategies for an image’s semantic description quality.
This book proposes a novel framework for the semantic description and annotation of digital images within the humanities computing field. The author addresses the limitations of current annotation methods, which suffer from low quality and inconsistency due to the absence of domain-specific hierarchical schemas and controlled vocabularies. The proposed framework integrates a semantic description schema with a domain thesaurus, aiming to improve the management and reuse of cultural digital images. The research specifically explores the relationship between semantic levels within this framework and tests its efficacy using digital images of Dunhuang frescoes, examining the impact of semantic granularity on annotation cost and quality control strategies.
The proposed framework aims to tackle the persistent challenges of low quality and inconsistency in digital image annotation within humanities computing. By combining a semantic description schema with a domain thesaurus, the research offers a structured approach to image content description. The application to Dunhuang frescoes suggests a practical method for improving image management and retrieval in cultural heritage contexts. The discussion on semantic granularity and quality control provides valuable insights for researchers and practitioners in the field.
Page Count:
52
Publication Date:
2018-09-05
Publisher:
LAP LAMBERT Academic Publishing
ISBN-10:
3330344156
ISBN-13:
9783330344150
No comments yet. Be the first to share your thoughts!