Share Email Print

Journal of Electronic Imaging

Detection of textured areas in natural images using an indicator based on component counts
Author(s): Ruth Bergman; Hila Nachlieli; Gitit Ruckenstein
Format Member Price Non-Member Price
PDF $20.00 $25.00

Paper Abstract

An algorithm is presented for the detection of textured areas in natural images. Texture detection has potential application to image enhancement, tone correction, defect detection, content classification, and image segmentation. For example, texture detection may be useful for object detection when combined with color models and other descriptors. Sky, e.g., is generally smooth, and foliage is textured. The texture detector presented here is based on the intuition that texture in a natural image is comprised of many components. The measure we develop examines the structure of local regions of the image. This structural approach enables us to detect both structured and unstructured textures at many scales. Furthermore, it distinguishes between edges and texture, and also between texture and noise. Automatic detection results are shown to match human classification of corresponding image areas.

Paper Details

Date Published: 1 October 2008
PDF: 13 pages
J. Electron. Imag. 17(4) 043003 doi: 10.1117/1.2981836
Published in: Journal of Electronic Imaging Volume 17, Issue 4
Show Author Affiliations
Ruth Bergman, Hewlett-Packard Labs. Israel Ltd. (Israel)
Hila Nachlieli, Hewlett-Packard Labs. Israel Ltd. (Israel)
Gitit Ruckenstein, Hewlett-Packard Labs. Israel Ltd. (Israel)

© SPIE. Terms of Use
Back to Top