Title :
Face Localization Using an Effective Co-evolutionary Genetic Algorithm
Author :
Hajati, Farshid ; Lucas, Caro ; Gao, Yongsheng
Author_Institution :
Fac. of Electr. Eng., Amirkabir Univ. of Technol., Tehran, Iran
Abstract :
In this paper, a new method for face localization in color images, which is based on co-evolutionary systems, is introduced. The proposed method uses a co-evolutionary system to locate the eyes in a face image. The used coevolutionary system involves two genetic algorithm models. The first GA model searches for a solution in the given environment, and the second GA model searches for useful genetic information in the first GA model. In the next step, by using the location of eyes in image the parameters of face´s bounding ellipse (center, orientation, major and minor axis) are computed. To evaluate and compare the proposed method with other methods, high order Pseudo Zernike Moments (PZM) are utilized to produce feature vectors and a Radial Basis Function (RBF) neural network is used as the classifier. Simulation results indicate that the speed and accuracy of the new system using the proposed face localization method which uses a co-evolutionary approach is higher than the system proposed in.
Keywords :
face recognition; genetic algorithms; image colour analysis; polynomials; radial basis function networks; Pseudo Zernike Moments; coevolutionary genetic algorithm; color images; face bounding ellipse; face localization; radial basis function neural network; Artificial neural networks; Face; Face recognition; Feature extraction; Gallium; Skin; Support vector machine classification; coevolutionary; face localization; genetic algorithm;
Conference_Titel :
Digital Image Computing: Techniques and Applications (DICTA), 2010 International Conference on
Conference_Location :
Sydney, NSW
Print_ISBN :
978-1-4244-8816-2
Electronic_ISBN :
978-0-7695-4271-3
DOI :
10.1109/DICTA.2010.116