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 proceedingConference 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 languageEnglish (US)
Title of host publicationProceedings - International Conference on Image Analysis and Processing, ICIAP 1999
Pages32-37
Number of pages6
DOIs
StatePublished - Dec 1 1999
Event10th International Conference on Image Analysis and Processing, ICIAP 1999 - Venice, Italy
Duration: Sep 27 1999Sep 29 1999

Publication series

NameProceedings - International Conference on Image Analysis and Processing, ICIAP 1999

Other

Other10th International Conference on Image Analysis and Processing, ICIAP 1999
CountryItaly
CityVenice
Period9/27/999/29/99

    Fingerprint

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition

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). [797567] (Proceedings - International Conference on Image Analysis and Processing, ICIAP 1999). https://doi.org/10.1109/ICIAP.1999.797567