by Xiaowen Ji, Zoltan Kato, Zhiyong Huang
Abstract:
In this paper, we will show how non-photorealistic rendering (NPR) can take a new role in content-based image retrieval (CBIR). The proposed CBIR method applies a novel image similarity measure: unlike traditional features like color, texture, or shape, our measure is based on a painted representation of the original image. This is produced by a stochastic paintbrush algorithm which simulates a painting process. We use the stroke parameters (color, size, orientation, and location) as features and similarity is measured by matching strokes of a pair of images. The advantage of our approach is that it provides information not only about the color content but also about the structural properties of an image without the segmentation of the image. Experimental results show that the CBIR method using paintbrush features has higher retrieval rate than traditional methods using color or texture features only.
Reference:
Xiaowen Ji, Zoltan Kato, Zhiyong Huang, Non-Photorealistic Rendering and Content-Based Image Retrieval, In Proceedings of Pacific Conference on Computer Graphics and Applications, Canmore, Canada, pp. 153-162, 2003.
Bibtex Entry:
@string{pg="Proceedings of Pacific Conference on Computer Graphics and Applications"}
@InProceedings{Ji-etal2003,
author = {Ji, Xiaowen and Kato, Zoltan and Huang, Zhiyong},
title = {Non-Photorealistic Rendering and Content-Based Image
Retrieval},
booktitle = pg,
pages = {153--162},
year = 2003,
address = {Canmore, Canada},
month = oct,
organization = {IEEE},
pdf = {papers/pg2003.pdf},
abstract = {In this paper, we will show how non-photorealistic
rendering (NPR) can take a new role in content-based
image retrieval (CBIR). The proposed CBIR method
applies a novel image similarity measure: unlike
traditional features like color, texture, or shape,
our measure is based on a painted representation of
the original image. This is produced by a stochastic
paintbrush algorithm which simulates a painting
process. We use the stroke parameters (color, size,
orientation, and location) as features and
similarity is measured by matching strokes of a pair
of images. The advantage of our approach is that it
provides information not only about the color
content but also about the structural properties of
an image without the segmentation of the
image. Experimental results show that the CBIR
method using paintbrush features has higher
retrieval rate than traditional methods using color
or texture features only.}
}