On RGB-D face recognition using Kinect

@article{Goswami2013OnRF,
  title={On RGB-D face recognition using Kinect},
  author={Gaurav Goswami and Samarth Bharadwaj and Mayank Vatsa and Richa Singh},
  journal={2013 IEEE Sixth International Conference on Biometrics: Theory, Applications and Systems (BTAS)},
  year={2013},
  pages={1-6}
}
Face recognition algorithms generally use 2D images for feature extraction and matching. [] Key Method The proposed algorithm computes a descriptor based on the entropy of RGB-D faces along with the saliency feature obtained from a 2D face. The probe RGB-D descriptor is used as input to a random decision forest classifier to establish the identity. This research also presents a novel RGB-D face database pertaining to 106 individuals. The experimental results indicate that the RGB-D information obtained by…

Figures and Tables from this paper

RGB-D Face Recognition With Texture and Attribute Features
TLDR
The experimental results indicate that the proposed algorithm achieves high face recognition accuracy on RGB-D images obtained using Kinect compared with existing 2D and 3D approaches.
A RGB-D face recognition approach without confronting the camera
TLDR
A 3D human face recognition algorithm using the Microsoft's Kinect that integrates the depth data with the RGB data to generate 3D face raw data and then extracts feature points, identifies the target via a two-level cascade classifier and builds a 3D-face database including 16 individuals captured exclusively using Kinect.
Face Recognition with RGB-D Images Using Kinect
TLDR
This chapter discusses existing RGB-D face recognition algorithms and presents a state-of-the-art algorithm based on extracting discriminatory features using entropy and saliency fromRGB-D images.
2D and 3D Face Recognition using Close-Range RGB-D Camera
TLDR
Close-range (of depth) camera is used for developing face recognition system, which can provide high recognition rate even in low-resolution images, and the fusion of RGB and Depth images improve the recognition rate.
3D Face Recognition using Kinect
TLDR
This work developed an algorithm based on modified SURF descriptors on RGB images combined with various enhancements on automatically generated training images using Depth and Color images to produce better results than existing 2D Face recognition techniques even after compromising on the quality of the images from the sensor.
Fusion of RGB and Depth Images for RobustFace Recognition using Close-Range 3DCamera
TLDR
It is found that two algorithms proposed have improved the recognition performance significantly and among all combinations of feature representations for RGB and depth images, two methods, HOG (RGB) +LDA (Depth) and LBP ( RGB) + LDA ( Depth), have performed better for fusion system.
An Efficient Face Recognition Using SIFT Descriptor in RGB-D Images
TLDR
This work proposes a new algorithm that combines the RGB image with Depth map which is less sensible to illumination changes, and gets a recognition rate of 96, 63% in rank 2.
RGB-D face recognition in surveillance videos
TLDR
The KaspAROV RGB-D video face database is introduced which provides face videos and images from Kinect device for over 100 subjects and generates a shared representation from RGB images which contains discriminative information from both the RGB and depth images.
Face Recognition Using 3DLBP Method Applied to Depth Maps Obtained from Kinect Sensors
TLDR
The main goal of this work was to assess the performance of 3DLBP method for face recognition when using depth maps generated by Kinect devices and investigate the face regions in which the depth maps contribute most to increase the face recognition rates.
...
...

References

SHOWING 1-10 OF 23 REFERENCES
An RGB-D Database Using Microsoft's Kinect for Windows for Face Detection
TLDR
An RGB-D database containing 1581 images (and their depth counterparts) taken from 31 persons in 17 different poses and facial expressions using a Kinect device is proposed and used in a face detection algorithm which is based on the depth information of the images.
An Efficient LBP-Based Descriptor for Facial Depth Images Applied to Gender Recognition Using RGB-D Face Data
TLDR
A novel efficient LBP-based descriptor, namely Gradient-L BP (G-LBP), specialized to encode the facial depth information inspired by 3DLBP, yet resolves its inherent drawbacks is proposed, applied to gender recognition task and shows its superiority to 3DL BP in all the experimental setups.
Using Kinect for face recognition under varying poses, expressions, illumination and disguise
TLDR
An algorithm is proposed which exploits the facial symmetry at the 3D point cloud level to obtain a canonical frontal view, shape and texture, of the faces irrespective of their initial pose, using a low resolution 3D sensor for robust face recognition under challenging conditions.
A Survey of 3D Face Recognition Methods
TLDR
The main purpose of this overview is to describe the recent 3D face recognition algorithms, which hold more information of the face, like surface information, that can be used for face recognition or subject discrimination.
Face recognition with learning-based descriptor
  • Zhimin Cao, Qi Yin, Xiaoou Tang, Jian Sun
  • Computer Science
    2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
  • 2010
TLDR
This work proposes a pose-adaptive matching method that uses pose-specific classifiers to deal with different pose combinations of the matching face pair, and finds that a simple normalization mechanism after PCA can further improve the discriminative ability of the descriptor.
Depth kernel descriptors for object recognition
TLDR
A set of kernel features on depth images that model size, 3D shape, and depth edges in a single framework that significantly improve the capabilities of depth and RGB-D (color+depth) recognition, achieving 10–15% improvement in accuracy over the state of the art.
Face Recognition Using Scale Invariant Feature Transform and Support Vector Machine
TLDR
A new method based on SIFT and support vector machine (SVM) for the face recognition problem is proposed, where first the SIFT features are generated and then SVM is used for the classification.
Texture-less object tracking with online training using an RGB-D camera
TLDR
A texture-less object detection and 3D tracking method which automatically extracts on the fly the information it needs from color images and the corresponding depth maps and automatically extracts a 3D model for the target from the depth information.
Descriptor Based Methods in the Wild
TLDR
This paper explores how well this performance carries over to the related task of multi-option face identification, specifically on the Labeled Faces in the Wild (LFW) image set, and seeks to compare the performance of similarity learning methods to descriptor based methods.
Robust Face Recognition via Sparse Representation
TLDR
This work considers the problem of automatically recognizing human faces from frontal views with varying expression and illumination, as well as occlusion and disguise, and proposes a general classification algorithm for (image-based) object recognition based on a sparse representation computed by C1-minimization.
...
...