Pre-attentive detection of perceptually important regions in facial images

Alexander Golovan, Myung Hyun Yoo, Seong Whan Lee

Research output: Contribution to journalArticlepeer-review


Cascade method, a new way of calculating orientation components in an image, was developed to extract some important regions from a given image of human face. By combining local orientation components and thresholding them, we construct five feature maps and a final composite map which is a linear combination of the five maps. As in human visual perception, the composite map operates like pre-attentive processing in early stage of vision, and then shows robustness in selecting the most informative areas of images. For 50 non-normalized face images from ORL1 database, it showed 91% of detecting accuracy which is the ratio of corresponding points between the feature maps of whole image and same maps of important regions in that image such as eyes, nose and mouth, etc.

Original languageEnglish
Pages (from-to)1092-1095
Number of pages4
JournalProceedings - International Conference on Pattern Recognition
Issue number1
Publication statusPublished - 2000

Bibliographical note

Funding Information:
*This research was supported by Creative Research Initiatives of the Ministry of Science and Technology, Korea. Olivetti research laboratory in Cambridge

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition


Dive into the research topics of 'Pre-attentive detection of perceptually important regions in facial images'. Together they form a unique fingerprint.

Cite this