2D&3D-ComFusFace: 2D and 3D Face Recognition by Scalable Fusion of Common Features
نویسندگان
چکیده
In traditional 2D and 3D face recognition systems, different features are extracted from 2D and 3D face images, and then are fused to improve the recognition performance. The shortage of these methods is that they neglect the intrinsic complementary features between 2D and 3D data. In this paper, we investigate the possibility of extracting and scalable fusing common features from 2D intensity and 3D depth face images, and develop a novel 2D and 3D face recognition method-2D&3D-ComFusFace, which represent and fuse some common global and local features of 2D and 3D data. A novel pose normalization method for 3D range data is also proposed before transiting them to be depth image. After preprocessing, two global features--2D Principle component Analysis (2DPCA), 2D Fisher Linear Discriminate Analysis (2DFLD), and a local feature--Local Binary Pattern (LBP) are extracted from both 2D intensity image and 3D depth image. Then the matching scores are computed and fused by weighted sum rule to get a further improved performance. The experiments are carried out on CASIA3D database, and significant improvements of both recognition rate and EER are achieved
منابع مشابه
Hand Gesture Recognition from RGB-D Data using 2D and 3D Convolutional Neural Networks: a comparative study
Despite considerable enhances in recognizing hand gestures from still images, there are still many challenges in the classification of hand gestures in videos. The latter comes with more challenges, including higher computational complexity and arduous task of representing temporal features. Hand movement dynamics, represented by temporal features, have to be extracted by analyzing the total fr...
متن کاملHybridization of Facial Features and Use of Multi Modal Information for 3D Face Recognition
Despite of achieving good performance in controlled environment, the conventional 3D face recognition systems still encounter problems in handling the large variations in lighting conditions, facial expression and head pose The humans use the hybrid approach to recognize faces and therefore in this proposed method the human face recognition ability is incorporated by combining global and local ...
متن کاملComparison of 2D/3D Features and Their Adaptive Score Level Fusion for 3D Face Recognition
3D face has been introduced in the literature to deal with the unsolved issues of 2D face recognition, namely lighting and pose variations. In this paper, we study and compare the distinctiveness of features extracted from both the registered 2D face images and 3D face models. Sparse Representation Classifier (SRC) is exploited to calculate all similarity measures which are compared with the on...
متن کاملLearning to Fuse 3D+2D Based Face Recognition at Both Feature and Decision Levels
2D intensity images and 3D shape models are both useful for face recognition, but in different ways. While algorithms have long been developed using 2D or 3D data, recently has seen work on combining both into multi-modal face biometrics to achieve higher performance. However, the fusion of the two modalities has mostly been at the decision level, based on scores obtained from independent 2D an...
متن کاملRobust Geometrically Invariant Features for 2 D Shape Matching and 3 D Face Recognition
Invariant features play a key role in object and pattern recognition studies. Features that are invariant to geometrical transformations offer succinct representations of underlying objects so that they can be reliably identified. In this dissertation, we introduce a family of novel invariant features based on Cartan’s theory of moving frames. We call these new features summation invariants. Co...
متن کامل