Multiresolution object-of-interest detection for images with low depth of field

Jia Li; James Ze Wang; Robert M. Gray; Gio Wiederhold

doi:10.1109/ICIAP.1999.797567

Multiresolution object-of-interest detection for images with low depth of field

Jia Li, James Ze Wang, Robert M. Gray, Gio Wiederhold

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

11 Scopus citations

Abstract

This paper describes a novel multiresolution image segmentation algorithm for separating sharply focused objects-of-interest from other foreground or background objects in low depth-of-field (DOF) images, such as sports, telephoto, macro, and microscopic images. The algorithm takes a multiscale context-dependent approach to segment images based on features extracted from wavelet coefficients in high-frequency bands. The algorithm is fully automatic in that all parameters are image-independent. Experiments with the algorithm on more than 100 low DOF images have shown results close to the human segmentation of these images. Besides high accuracy, the algorithm also provides high speed. A 768 ×512 pixel image can be segmented within two seconds on a Pentium Pro 300 MHz PC.

Original language	English (US)
Title of host publication	Proceedings - International Conference on Image Analysis and Processing, ICIAP 1999
Pages	32-37
Number of pages	6
DOIs	https://doi.org/10.1109/ICIAP.1999.797567
State	Published - 1999
Event	10th International Conference on Image Analysis and Processing, ICIAP 1999 - Venice, Italy Duration: Sep 27 1999 → Sep 29 1999

Publication series

Name	Proceedings - International Conference on Image Analysis and Processing, ICIAP 1999

Other

Other	10th International Conference on Image Analysis and Processing, ICIAP 1999
Country/Territory	Italy
City	Venice
Period	9/27/99 → 9/29/99

All Science Journal Classification (ASJC) codes

Computer Vision and Pattern Recognition

Access to Document

10.1109/ICIAP.1999.797567

Cite this

Li, J., Wang, J. Z., Gray, R. M., & Wiederhold, G. (1999). Multiresolution object-of-interest detection for images with low depth of field. In Proceedings - International Conference on Image Analysis and Processing, ICIAP 1999 (pp. 32-37). Article 797567 (Proceedings - International Conference on Image Analysis and Processing, ICIAP 1999). https://doi.org/10.1109/ICIAP.1999.797567

@inproceedings{47c1bf10911c4635a66d8ef95e2646fd,

title = "Multiresolution object-of-interest detection for images with low depth of field",

abstract = "This paper describes a novel multiresolution image segmentation algorithm for separating sharply focused objects-of-interest from other foreground or background objects in low depth-of-field (DOF) images, such as sports, telephoto, macro, and microscopic images. The algorithm takes a multiscale context-dependent approach to segment images based on features extracted from wavelet coefficients in high-frequency bands. The algorithm is fully automatic in that all parameters are image-independent. Experiments with the algorithm on more than 100 low DOF images have shown results close to the human segmentation of these images. Besides high accuracy, the algorithm also provides high speed. A 768 ×512 pixel image can be segmented within two seconds on a Pentium Pro 300 MHz PC.",

author = "Jia Li and Wang, {James Ze} and Gray, {Robert M.} and Gio Wiederhold",

year = "1999",

doi = "10.1109/ICIAP.1999.797567",

language = "English (US)",

isbn = "0769500404",

series = "Proceedings - International Conference on Image Analysis and Processing, ICIAP 1999",

pages = "32--37",

booktitle = "Proceedings - International Conference on Image Analysis and Processing, ICIAP 1999",

}

Li, J , Wang, JZ, Gray, RM & Wiederhold, G 1999, Multiresolution object-of-interest detection for images with low depth of field. in Proceedings - International Conference on Image Analysis and Processing, ICIAP 1999., 797567, Proceedings - International Conference on Image Analysis and Processing, ICIAP 1999, pp. 32-37, 10th International Conference on Image Analysis and Processing, ICIAP 1999, Venice, Italy, 9/27/99. https://doi.org/10.1109/ICIAP.1999.797567

Multiresolution object-of-interest detection for images with low depth of field. / Li, Jia ; Wang, James Ze; Gray, Robert M. et al.
Proceedings - International Conference on Image Analysis and Processing, ICIAP 1999. 1999. p. 32-37 797567 (Proceedings - International Conference on Image Analysis and Processing, ICIAP 1999).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Multiresolution object-of-interest detection for images with low depth of field

AU - Li, Jia

AU - Wang, James Ze

AU - Gray, Robert M.

AU - Wiederhold, Gio

PY - 1999

Y1 - 1999

N2 - This paper describes a novel multiresolution image segmentation algorithm for separating sharply focused objects-of-interest from other foreground or background objects in low depth-of-field (DOF) images, such as sports, telephoto, macro, and microscopic images. The algorithm takes a multiscale context-dependent approach to segment images based on features extracted from wavelet coefficients in high-frequency bands. The algorithm is fully automatic in that all parameters are image-independent. Experiments with the algorithm on more than 100 low DOF images have shown results close to the human segmentation of these images. Besides high accuracy, the algorithm also provides high speed. A 768 ×512 pixel image can be segmented within two seconds on a Pentium Pro 300 MHz PC.

AB - This paper describes a novel multiresolution image segmentation algorithm for separating sharply focused objects-of-interest from other foreground or background objects in low depth-of-field (DOF) images, such as sports, telephoto, macro, and microscopic images. The algorithm takes a multiscale context-dependent approach to segment images based on features extracted from wavelet coefficients in high-frequency bands. The algorithm is fully automatic in that all parameters are image-independent. Experiments with the algorithm on more than 100 low DOF images have shown results close to the human segmentation of these images. Besides high accuracy, the algorithm also provides high speed. A 768 ×512 pixel image can be segmented within two seconds on a Pentium Pro 300 MHz PC.

UR - http://www.scopus.com/inward/record.url?scp=84890394331&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84890394331&partnerID=8YFLogxK

U2 - 10.1109/ICIAP.1999.797567

DO - 10.1109/ICIAP.1999.797567

M3 - Conference contribution

AN - SCOPUS:84890394331

SN - 0769500404

SN - 9780769500409

T3 - Proceedings - International Conference on Image Analysis and Processing, ICIAP 1999

SP - 32

EP - 37

BT - Proceedings - International Conference on Image Analysis and Processing, ICIAP 1999

T2 - 10th International Conference on Image Analysis and Processing, ICIAP 1999

Y2 - 27 September 1999 through 29 September 1999

ER -

Multiresolution object-of-interest detection for images with low depth of field

Abstract

Publication series

Other

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this