2015 | OriginalPaper | Buchkapitel
Exploring Deep Gradient Information for Face Recognition
verfasst von : Jianjun Qian, Jian Yang, Ying Tai
Erschienen in: Computer Vision
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
This paper presents a novel and simple image feature extraction method, called exploring deep gradient information (DGI), for face recognition. DGI first captures the local structure of an image by computing the histogram of gradient orientation of each macro-pixel (local patch around the central pixel). One image can be decomposed into L sub-images (also called orientation images) according to the structure information of each macro-pixel since there are L bins in the local histogram. For each orientation image, dense scale invariant feature transform (DSIFT) is used to further explore the gradient orientation information. All DSIFT feature are concatenated into one augmented super-vector. Finally, dimensionality reduction technology is applied to obtain the low-dimensional and discriminative feature vector. We evaluated the proposed method on the real-world face image datasets NUST-RWFR, Pubfig and LFW. In all experiments, DGI achieves competitive results compared with state-of-the-art algorithms.