Date of Submission
Fall 2014
Academic Programs and Concentrations
Computer Science
Project Advisor 1
Keith O'Hara
Abstract/Artist's Statement
Painting classification is a novel subfield of research in computer vision and image processing that focuses on empirically defining a painting's authorship, date of creation, or genre. The applications of the subfield have increased in response to changing art markets and expanding and emerging research. Basic features like color and line in and of themselves prove inadequate in this study. Texture analysis provides one of the promising additional features. In this paper, I specifically investigate two different measures of texture analysis, Gabor filters and Haralick features, in addition to basic features, and their applications in a specific painting classification problem. I also consider different methods of collecting this data, and the impact of each on classification.
Open Access Agreement
On-Campus only
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.
Recommended Citation
Fauber, Jacob, "Feature Extraction and Texture Analysis in the Classification of Paintings" (2014). Senior Projects Fall 2014. 35.
https://digitalcommons.bard.edu/senproj_f2014/35
This work is protected by a Creative Commons license. Any use not permitted under that license is prohibited.
Bard Off-campus DownloadBard College faculty, staff, and students can login from off-campus by clicking on the Off-campus Download button and entering their Bard username and password.