Gradient feature extraction for classification-based face detection

✍ Scribed by Lin-Lin Huang; Akinobu Shimizu; Yoshihoro Hagihara; Hidefumi Kobatake

• Publisher: Elsevier Science
• Year: 2003
• Tongue: English
• Weight: 668 KB
• Volume: 36
• Category: Article
• ISSN: 0031-3203
• DOI: 10.1016/s0031-3203(03)00130-4

✦ Synopsis

Face detection from cluttered images is challenging due to the wide variability of face appearances and the complexity of image backgrounds. This paper proposes a classiÿcation-based method for locating frontal faces in cluttered images. To improve the detection performance, we extract gradient direction features from local window images as the input of the underlying two-class classiÿer. The gradient direction representation provides better discrimination ability than the image intensity, and we show that the combination of gradient directionality and intensity outperforms the gradient feature alone. The underlying classiÿer is a polynomial neural network (PNN) on a reduced feature subspace learned by principal component analysis (PCA). The incorporation of the residual of subspace projection into the PNN was shown to improve the classiÿcation performance. The classiÿer is trained on samples of face and non-face images to discriminate between the two classes. The superior detection performance of the proposed method is justiÿed in experiments on a large number of images.