Eye position detection method and device
AssigneeMatsushita Electric Industrial Co., Ltd.
InventorsKenji Kondo, Kenya Uomori
Life of this patent
Estimating the term…
Abstract
The position of an eye is detectable with high precision from a face image of a person taken under near infrared illumination or the like. After pre-processing, the face image is subjected to brightness correction to increase the contrast between the sclera portion and iris portion of the eye. Brightness gradient vectors are calculated for the brightness-corrected image, and matching is performed between a brightness gradient image generated using the calculated brightness gradient vectors and an eye template. Further, matching with a pupil template is performed to correct the eye center position. Final positions of both eyes are then determined.
Claims12
A method for detecting an eye position from a face image including at least an eye area, the face image being taken under near infrared light, comprising the steps of:
- performing brightness correction for part or the entire of the face image to increase the contrast between a sclera portion and an iris portion of the eye;
- calculating brightness gradient vectors for the brightness-corrected face image;
- and
- performing matching between a brightness gradient image generated using the calculated brightness gradient vectors and an eye template,
- wherein the eye position is detected based on the results of the matching,
- wherein the brightness correction step includes the steps of:
- calculating a brightness gradient for each pixel in a part of the face image for brightness correction;
- generating an expression for conversion for histogram equalization using some of pixels in the part, the some pixels being a top A percent of the pixels in the part ranked according to a brightness gradient intensity where A is a predetermined value;
- and
- performing histogram equalization for all pixels in the part using the generated expression for conversion.
A device for detecting an eye position from a face image including at least an eye area, the face image being taken under near infrared light, comprising:
- means for performing brightness correction for part or the entire of the face image to increase the contrast between a sclera portion and an iris portion of an eye;
- means for calculating brightness gradient vectors from the brightness-corrected face image;
- and
- means for performing matching between a brightness gradient image generated using the calculated brightness gradient vectors and an eye template,
- wherein the eye position is detected based on the results of the matching,
- wherein the brightness correction means performs the steps of:
- calculating a brightness gradient for each pixel in a part of the face image for brightness correction;
- generating an expression for conversion for histogram equalization using some of pixels in the part, the some pixels being a top A percent of the pixels in the part ranked according to a brightness gradient intensity where A is a predetermined value;
- and
- performing histogram equalization for all pixels in the part using the generated expression for conversion.
Dependencies are inferred from the claim text.