Facial Features Detection Using Heuristic Cost Function


The KIPS Transactions:PartB , Vol. 8, No. 2, pp. 183-188, Apr. 2001
10.3745/KIPSTB.2001.8.2.183,   PDF Download:

Abstract

This paper proposes a efficient method for detecting pupils and recognizing facial features, such as location of eyes and mouth. Pupils are detected using features based on the eye's shape and facial features are recognized using a cost function based on the property of face. Supervised pixel-based classifications are employed to mark all pixels that are within predefined distances of skin color and lip color respectively. A pupil is detected using a function based on the difference of gray levels between pupil and sclera. Finally, a cost function is introduced to search eyes and mouse. The experiments have been performed for many images, and show very encouraging result.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from September 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article
[IEEE Style]
K. S. Jang, "Facial Features Detection Using Heuristic Cost Function," The KIPS Transactions:PartB , vol. 8, no. 2, pp. 183-188, 2001. DOI: 10.3745/KIPSTB.2001.8.2.183.

[ACM Style]
Kyung Shik Jang. 2001. Facial Features Detection Using Heuristic Cost Function. The KIPS Transactions:PartB , 8, 2, (2001), 183-188. DOI: 10.3745/KIPSTB.2001.8.2.183.