Kinect vs Lytro in RGB-D Face Recognition

Chiesa, Valeria; Dugelay, Jean‐Luc

doi:10.1109/cw.2018.00069

Cited by 2 publications

(3 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among the constrained RGB-D datasets listed in Table II, Texas 3D [63], Eurecom Kinect face [34], and VAP [64] are relatively small, while BU-3DFE [62] and FaceWarehouse [65] are specifically designed for facial emotion recognition, which prevents their usage in our experiments. Additionally, it has been proven that the rendered depth images from light field multi-view data are not as effective as Kinect data for FR [67], so we also excluded LFFD [66] from our experiments. To this end, we have conducted our experiments on the remaining three constrained datasets, i.e.…”

Section: Rgb-d Face Datasetsmentioning

confidence: 99%

Depth as Attention for Face Representation Learning

Uppal

Sepas-Moghaddam

Greenspan

et al. 2021

IEEE Trans.Inform.Forensic Secur.

View full text Add to dashboard Cite

Face representation learning solutions have recently achieved great success for various applications such as verification and identification. However, face recognition approaches that are based purely on RGB images rely solely on intensity information, and therefore are more sensitive to facial variations, notably pose, occlusions, and environmental changes such as illumination and background. A novel depth-guided attention mechanism is proposed for deep multi-modal face recognition using low-cost RGB-D sensors. Our novel attention mechanism directs the deep network "where to look" for visual features in the RGB image by focusing the attention of the network using depth features extracted by a Convolution Neural Network (CNN). The depth features help the network focus on regions of the face in the RGB image that contain more prominent person-specific information. Our attention mechanism then uses this correlation to generate an attention map for RGB images from the depth features extracted by the CNN. We test our network on four public datasets, showing that the features obtained by our proposed solution yield better results on the Lock3DFace, CurtinFaces, IIIT-D RGB-D, and KaspAROV datasets which include challenging variations in pose, occlusion, illumination, expression, and time lapse. Our solution achieves average (increased) accuracies of 87.3% (+5.0%), 99.1% (+0.9%), 99.7% (+0.6%) and 95.3%(+0.5%) for the four datasets respectively, thereby improving the state-of-the-art. We also perform additional experiments with thermal images, instead of depth images, showing the high generalization ability of our solution when adopting other modalities for guiding the attention mechanism instead of depth information.

show abstract

Section: Rgb-d Face Datasetsmentioning

confidence: 99%

Depth as Attention for Face Representation Learning

Uppal

Sepas-Moghaddam

Greenspan

et al. 2021

IEEE Trans.Inform.Forensic Secur.

View full text Add to dashboard Cite

show abstract

“…This feature, although not yet widely investigated, could be used to adapt and develop novel 3D face analysis techniques for light fields. A first step in this direction is described in [21], where the authors have compared the performances of a set of state-of-art algorithms for 2D and 3D face recognition on face images collected with two RGB-D sensors, which are a light-field camera and the Microsoft Kinect V1 (Read more at ). Regarding the 3D information, the Kinect embeds a structured light 3D scanner.…”

Section: Introductionmentioning

confidence: 99%

“…The 3D information is collected by projecting a known light pattern on the scene and analyzing how this pattern is deformed after hitting a surface. The results presented in [21], show that light fields are more robust than Kinect when dealing with facial occlusions (e.g., sunglasses). For a recent overview of 3D face recognition, the reader is referred to [22,23].…”

Section: Introductionmentioning

confidence: 99%

Light Fields for Face Analysis

Galdi

Chiesa

Busch

et al. 2019

Sensors

Self Cite

View full text Add to dashboard Cite

The term “plenoptic” comes from the Latin words plenus (“full”) + optic. The plenoptic function is the 7-dimensional function representing the intensity of the light observed from every position and direction in 3-dimensional space. Thanks to the plenoptic function it is thus possible to define the direction of every ray in the light-field vector function. Imaging systems are rapidly evolving with the emergence of light-field-capturing devices. Consequently, existing image-processing techniques need to be revisited to match the richer information provided. This article explores the use of light fields for face analysis. This field of research is very recent but already includes several works reporting promising results. Such works deal with the main steps of face analysis and include but are not limited to: face recognition; face presentation attack detection; facial soft-biometrics classification; and facial landmark detection. This article aims to review the state of the art on light fields for face analysis, identifying future challenges and possible applications.

show abstract

Kinect vs Lytro in RGB-D Face Recognition

Cited by 2 publications

References 22 publications

Depth as Attention for Face Representation Learning

Depth as Attention for Face Representation Learning

Light Fields for Face Analysis

Contact Info

Product

Resources

About