3DOR: Eurographics Workshop on 3D Object Retrieval

Permanent URI for this community

https://diglib.eg.org/handle/10.2312/307

Browse

Browsing 3DOR: Eurographics Workshop on 3D Object Retrieval by Subject "Biometrics"

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Depth-Based Face Recognition by Learning from 3D-LBP Images
    (The Eurographics Association, 2019) Neto, Joao Baptista Cardia; Marana, Aparecido Nilceu; Ferrari, Claudio; Berretti, Stefano; Bimbo, Alberto Del; Biasotti, Silvia and Lavoué, Guillaume and Veltkamp, Remco
    In this paper, we propose a hybrid framework for face recognition from depth images, which is both effective and efficient. It consists of two main stages: First, the 3DLBP operator is applied to the raw depth data of the face, and used to build the corresponding descriptor images (DIs). However, such operator quantizes relative depth differences over/under +-7 to the same bin, so as to generate a fixed dimensional descriptor. To account for this behavior, we also propose a modification of the traditional operator that encodes depth differences using a sigmoid function. Then, a not-so-deep (shallow) convolutional neural network (SCNN) has been designed that learns from the DIs. This architecture showed two main advantages over the direct application of deep-CNN (DCNN) to depth images of the face: On the one hand, the DIs are capable of enriching the raw depth data, emphasizing relevant traits of the face, while reducing their acquisition noise. This resulted decisive in improving the learning capability of the network; On the other, the DIs capture low-level features of the face, thus playing the role for the SCNN as the first layers do in a DCNN architecture. In this way, the SCNN we have designed has much less layers and can be trained more easily and faster. Extensive experiments on low- and high-resolution depth face datasets confirmed us the above advantages, showing results that are comparable or superior to the state-of-the-art, using by far less training data, time, and memory occupancy of the network.
  • Thumbnail Image
    Item
    Performing Image-like Convolution on Triangular Meshes
    (The Eurographics Association, 2018) Tortorici, Claudio; Werghi, Naoufel; Berretti, Stefano; Telea, Alex and Theoharis, Theoharis and Veltkamp, Remco
    Image convolution with a filtering mask is at the base of several image analysis operations. This is motivated by Mathematical foundations and by the straightforward way the discrete convolution can be computed on a grid-like domain. Extending the convolution operation to the mesh manifold support is a challenging task due to the irregular structure of the mesh connections. In this paper, we propose a computational framework that allows convolutional operations on the mesh. This relies on the idea of ordering the facets of the mesh so that a shift-like operation can be derived. Experiments have been performed with several filter masks (Sobel, Gabor, etc.) showing state-of-the-art results in 3D relief patterns retrieval on the SHREC'17 dataset. We also provide evidence that the proposed framework can enable convolution and pooling-like operations as can be needed for extending Convolutional Neural Networks to 3D meshes.
  • Thumbnail Image
    Item
    Person Re-Identification from Depth Cameras using Skeleton and 3D Face Data
    (The Eurographics Association, 2018) Pala, Pietro; Seidenari, Lorenzo; Berretti, Stefano; Bimbo, Alberto Del; Telea, Alex and Theoharis, Theoharis and Veltkamp, Remco
    In the typical approach, person re-identification is performed using appearance in 2D still images or videos, thus invalidating any application in which a person may change dress across subsequent acquisitions. For example, this is a relevant scenario for home patient monitoring. Depth cameras enable person re-identification exploiting 3D information that captures biometric cues such as face and characteristic dimensions of the body. Unfortunately, face and skeleton quality is not always enough to grant a correct recognition from depth data. Both features are affected by the pose of the subject and the distance from the camera. In this paper, we propose a model to incorporate a robust skeleton representation with a highly discriminative face feature, weighting samples by their quality. Our method combining face and skeleton data improves rank-1 accuracy compared to individual cues especially on short realistic sequences.