Fast Landmark Localization with 3D Component Reconstruction and CNN for Cross-Pose Recognition
نویسندگان
چکیده
Two approaches are proposed for cross-pose face recognition, one is based on the 3D reconstruction of facial components and the other is based on the deep Convolutional Neural Network (CNN). Unlike most 3D approaches that consider holistic faces, the proposed approach considers 3D facial components. It segments a 2D gallery face into components, reconstructs the 3D surface for each component, and recognizes a probe face by component features. The segmentation is based on the landmarks located by a hierarchical algorithm that combines the Faster R-CNN for face detection and the Reduced Tree Structured Model for landmark localization. The core part of the CNN-based approach is a revised VGG network. We study the performances with different settings on the training set, including the synthesized data from 3D reconstruction, the real-life data from an in-the-wild database, and both types of data combined. We investigate the performances of the network when it is employed as a classifier or designed as a feature extractor. The two recognition approaches and the fast landmark localization are evaluated in extensive experiments, and compared to stateof-the-art methods to demonstrate their efficacy.
منابع مشابه
Disentangling 3D Pose in A Dendritic CNN for Unconstrained 2D Face Alignment
Heatmap regression has been used for landmark localization for quite a while now. Most of the methods use a very deep stack of bottleneck modules for heatmap classification stage, followed by heatmap regression to extract the keypoints. In this paper, we present a single dendritic CNN, termed as Pose Conditioned Dendritic Convolution Neural Network (PCD-CNN), where a classification network is f...
متن کاملHyperFace: A Deep Multi-task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and Gender Recognition
We present an algorithm for simultaneous face detection, landmarks localization, pose estimation and gender recognition using deep convolutional neural networks (CNN). The proposed method called, Hyperface, fuses the intermediate layers of a deep CNN using a separate CNN and trains multi-task loss on the fused features. It exploits the synergy among the tasks which boosts up their individual pe...
متن کاملNosePose: a competitive, landmark-free methodology for head pose estimation in the wild
We perform head pose estimation solely based on the nose region as input, extracted from 2D images in unconstrained environments. Such information is useful for many face analysis applications, such as recognition, reconstruction, alignment, tracking and expression recognition. Using the nose region has advantages over using the whole face; not only it is less likely to be occluded by acesssori...
متن کاملFace frontalization for Alignment and Recognition
Recently, it was shown that excellent results can be achieved in both face landmark localization and pose-invariant face recognition. These breakthroughs are attributed to the efforts of the community to manually annotate facial images in many different poses and to collect 3D faces data. In this paper, we propose a novel method for joint face landmark localization and frontal face reconstructi...
متن کاملFacial Landmark Localization
Face detection and recognition is a vibrant area of biometrics with active research and commercial efforts over the last 20 years. The task of face detection is to search faces in images, reporting their positions by a bounding box. Recent studies [19, 31] have shown that face detection has already been a state-of-the-art technology in both accuracy and speed. However, face detection is not suf...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
- CoRR
دوره abs/1708.09580 شماره
صفحات -
تاریخ انتشار 2017