Budget Amount *help |
¥2,100,000 (Direct Cost: ¥2,100,000)
Fiscal Year 2000: ¥800,000 (Direct Cost: ¥800,000)
Fiscal Year 1999: ¥1,300,000 (Direct Cost: ¥1,300,000)
|
Research Abstract |
(1) First, we proposed an algorithm to detect faces in a color image with a complex background. The algorithm models faces by upright ellipses. And, inside each ellipse, a hair region and a skin region are defined. Generating ellipses, the algorithm computes a score for each ellipse. The score is given by the sum of three terms. The first term measures the fit of the boundary of the hair region to the edge map. The second term measures the fit of the skin region to the color map. The third term measures the fit of the hair region to the intensity map. And, the algorithm selects the candidates of faces from the generated ellipses according to nonincreasing order of their scores. (2) Secondly, we proposed a new algorithm to detect the irises of both eyes from a human face in an intensity image. Using the separability filter, the algorithm first extracts intensity valleys, called blobs. Next, for each pair of blobs, the algorithm computes a cost using Hough transform and separability filter to measure the fit of the pair of blobs to the image. And then, the algorithm selects a pair of blobs with the smallest cost as the irises of both eyes. (3) Thirdly, we proposed a system to identify the unknown person in a face image for which the position, scale and image-plane rotation of the face are unknown. The proposed system first detects the irises of both eyes using the algorithm described above and then normalizes the position, scale and image-plane rotation of the face in the image using the position of the irises of both eyes. After that, the system measures the degree of match between the image and the face template of each person and determines a person with the highest degree of match to be the unknown person in the image.
|