Studying Digital Imagery of Ancient Paintings
by Mixtures of Stochastic Models

Jia Li, James Z. Wang
The Pennsylvania State University, University Park, PA 16802

Abstract:

This paper addresses learning based characterization of fine art painting styles. The research has the potential to provide a powerful tool to art historians for studying connections among artists or periods in the history of art. Depending on specific applications, paintings can be categorized in different ways. In this paper, we focus on comparing the painting styles of artists. To profile the style of an artist, a mixture of stochastic models is estimated using training images. The 2-D multiresolution hidden Markov model (MHMM) is used in the experiment. These models form an artist's distinct digital signature. For certain types of paintings, only strokes provide reliable information to distinguish artists. Chinese ink paintings are a prime example of the above phenomenon; they do not have colors or even tones. The 2-D MHMM analyzes relatively large regions in an image, which in turn makes it more likely to capture properties of the painting strokes. The mixtures of 2-D MHMMs established for artists can be further used to classify paintings and compare paintings or artists. We implemented and tested the system using high-resolution digital photographs of some of China's most renowned artists. Experiments have demonstrated good potential of our approach in automatic analysis of paintings. Our work can be applied to other domains.


Full Paper
(high resolution PDF, 1.1MB)

Full Paper
(IEEE PDF, 0.9MB)

On-line Info


The copyrights of the images of ancient works belong to the museums or the owners of the images. Some images are used in the project under teaching, scholarship or research, which are considered as "Fair Use" because (1) the amount of copyrighted work used is reasonable, (2) the importance of that part of the work is not substantial to the whole work, and (3) the effect of the use upon the value or potential value of the copyrighted work is not significant. (See 17 U.S.C.A. 107).

Citation: Jia Li and James Z. Wang, ``Studying Digital Imagery of Ancient Paintings by Mixtures of Stochastic Models,'' IEEE Transactions on Image Processing, vol. 13, no. 3, pp. 340-353, 2004.

Copyright 2003 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works, must be obtained from the IEEE.

Last Modified: October 8, 2003
2003