15,302 Hits in 4.2 sec

Improved RGB-D-T based face recognition

Marc Oliu Simón, Ciprian Corneanu, Kamal Nasrollahi, Olegs Nikisins, Sergio Escalera, Yunlian Sun, Haiqing Li, Zhenan Sun, Thomas B. Moeslund, Modris Greitans
2016 IET Biometrics  
RGB-D-T database.  ...  This paper combines the latest successes in both directions by applying deep learning Convolutional Neural Networks (CNN) to the multimodal RGB-D-T based facial recognition problem outperforming previously  ...  However, in this paper, we focused on the RGB-D-T based face recognition.  ... 
doi:10.1049/iet-bmt.2015.0057 fatcat:txwr6cmhjrd7lkl2iavziq3ooq

Robust RGB-D Face Recognition Using Attribute-Aware Loss [article]

Luo Jiang, Juyong Zhang, Bailin Deng
2019 arXiv   pre-print
We train our face recognition model on a large-scale RGB-D data set with over 100K identities captured under real application conditions.  ...  In this paper, we propose a new CNN-based face recognition approach that incorporates such attributes into the training process.  ...  RGB-D Face Recognition In recent years, RGB-D based face recognition has attracted increasing attention because of its robustness in an unconstrained environment. Hsu et al.  ... 
arXiv:1811.09847v2 fatcat:asuc7a2aqja4xossvlbqrzkegu

Teacher-Student Adversarial Depth Hallucination to Improve Face Recognition [article]

Hardik Uppal, Alireza Sepas-Moghaddam, Michael Greenspan, Ali Etemad
2021 arXiv   pre-print
The fully trained shared generator can then be used in runtime to hallucinate depth from RGB for downstream applications such as face recognition.  ...  Moreover, face recognition experiments demonstrate that our hallucinated depth along with the input RGB images boosts performance across various architectures when compared to a single RGB modality by  ...  RGB-D Face Recognition Early RGB-D facial recognition methods were proposed based on classical (non-deep) methods. Goswami et al.  ... 
arXiv:2104.02424v2 fatcat:ehycefwn5nht3crjtdqqv4fida

Face recognition robust to head pose changes based on the RGB-D sensor

Cesare Ciaccio, Lingyun Wen, Guodong Guo
2013 2013 IEEE Sixth International Conference on Biometrics: Theory, Applications and Systems (BTAS)  
We propose an approach to face recognition robust to head rotations utilizing the RGB-D face images.  ...  ., the recent RGB-D cameras, we study the advantage of using RGB-D images for face recognition, focusing on the challenge of 3D head pose variations.  ...  Our major contributions in this paper include (1) a study of pose-invariant face recognition based on the RGB-D face images; (2) an appropriate scheme for head rotation in RGB-D images; and (3) a new face  ... 
doi:10.1109/btas.2013.6712718 dblp:conf/btas/CiaccioWG13 fatcat:zzvclf6kr5c4pp5hozxzaqt7gu

Face Recognition Using a Color Subspace LDA Approach

M. Thomas, C. Kambhamettu, S. Kumar
2008 2008 20th IEEE International Conference on Tools with Artificial Intelligence  
This paper delves into the problem of face recognition using color as an important cue in improving the accuracy of recognition.  ...  To test the accuracy of our methodology, we computed the recognition rate across two color face databases.  ...  (C, D) E RR S T 1 T 2 1D-PCA Gray, - 15 73.38 9.75 0.092 0.034 1D-PCA RGB, -15 75.24 21.34 0.26 0.064 1D-PCA HSV, - 15 82.27 21.6 0.26 0.064 1D-PCA YIQ, - 15 75.0 21.3 0.26 0.067 1D-PCA  ... 
doi:10.1109/ictai.2008.146 dblp:conf/ictai/ThomasKK08 fatcat:qshoxxi7xzelfnxfsif5e7bwua

Color space normalization: Enhancing the discriminating power of color spaces for face recognition

Jian Yang, Chengjun Liu, Lei Zhang
2010 Pattern Recognition  
Specifically, the normalized RGB, XYZ, XGB, and ZRG color spaces are more effective than or as effective as the I 1 I 2 I 3 , YUV, YIQ and LSLM color spaces for face recognition.  ...  Different color spaces usually display different discriminating power, and our experiments on a large scale face recognition grand challenge (FRGC) problem reveal that the RGB and XYZ color spaces are  ...  The results in [45] further demonstrate that color cues can significantly improve recognition performance compared with intensity-based features for coping with low-resolution face images.  ... 
doi:10.1016/j.patcog.2009.11.014 fatcat:3fafjfjeavbl7otrxvrvskzuvi

RGB-D-T Based Face Recognition

Olegs Nikisins, Kamal Nasrollahi, Modris Greitans, Thomas B. Moeslund
2014 2014 22nd International Conference on Pattern Recognition  
The current literature on facial image analysis, from face detection to face and facial expression recognition, are mainly performed in either RGB, Depth (D), or both of these modalities.  ...  This paper paves the way for performing such facial analyzes using synchronized RGB-D-T facial images by introducing a database of 51 persons including facial images of different rotations, illuminations  ...  D T All RGB D T All RGB D T All RGB D T All WNNC Rot.  ... 
doi:10.1109/icpr.2014.302 dblp:conf/icpr/NikisinsNGM14 fatcat:hytqdrrwuvbjxdkfcigq2332pq

Two-Level Attention-based Fusion Learning for RGB-D Face Recognition [article]

Hardik Uppal, Alireza Sepas-Moghaddam, Michael Greenspan, Ali Etemad
2020 arXiv   pre-print
With recent advances in RGB-D sensing technologies as well as improvements in machine learning and fusion techniques, RGB-D facial recognition has become an active area of research.  ...  A novel attention aware method is proposed to fuse two image modalities, RGB and depth, for enhanced RGB-D facial recognition.  ...  CONCLUSION AND FUTURE WORK We presented an attention-based network to effectively fuse the RGB and depth modalities of RGB-D images for face recognition.  ... 
arXiv:2003.00168v3 fatcat:lhhh3v5z25atxo6423frplny64

Spatiotemporal analysis of RGB-D-T facial images for multimodal pain level recognition

Ramin Irani, Kamal Nasrollahi, Marc O. Simon, Ciprian A. Corneanu, Sergio Escalera, Chris Bahnsen, Dennis H. Lundtoft, Thomas B. Moeslund, Tanja L. Pedersen, Maria-Louise Klitgaard, Laura Petrini
2015 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
While most available computer vision techniques are based on RGB, in this paper, we investigate the effect of combining RGB, depth, and thermal facial images for pain intensity level recognition.  ...  by more than 6% the results that only consider RGB data.  ...  These three pain indexes are then fused together to recognize the pain level using: P I = w RGB P I RGB + w D P I D + w T P I T , (9) where w RGB , w I , w T are the weights associated to corresponding  ... 
doi:10.1109/cvprw.2015.7301341 dblp:conf/cvpr/IraniNSCEBLMPKP15 fatcat:3jekokhcuzbsnmr3dasaez3kvq

User Identification and Object Recognition in Clutter Scenes Based on RGB-Depth Analysis [chapter]

Albert Clapés, Miguel Reyes, Sergio Escalera
2012 Lecture Notes in Computer Science  
We propose an automatic system for user identification and object recognition based on multi-modal RGB-Depth data analysis.  ...  We model a RGBD environment learning a pixel-based background Gaussian distribution.  ...  Supposing a RGBD Gaussian distribution for each pixel, the training procedure is performed as, μ x,t = (1 − α)μ x,t−1 + α D x,t max D t ∪ I x,t , (1) σ 2 x,t = (1 − α)σ 2 x,t−1 + α D x,t max D t ∪ I x,  ... 
doi:10.1007/978-3-642-31567-1_1 fatcat:nmcatezrqbdqjcwqcspyrikbcq

A Local Feature-Based Robust Approach for Facial Expression Recognition from Depth Video

2016 KSII Transactions on Internet and Information Systems  
For video-based facial expression recognition, depth cameras can be better candidates over RGB cameras as a person's face cannot be easily recognized from distance-based depth videos hence depth cameras  ...  also resolve some privacy issues that can arise using RGB faces.  ...  However, LBP-based features on RGB images can produce good recognition results for a person's face recognition rather than facial expression recognition.  ... 
doi:10.3837/tiis.2016.03.026 fatcat:mdtlpo2eqneljmfvbypenxvcce

Sign language recognition using dynamic time warping and hand shape distance based on histogram of oriented gradient features

Pat Jangyodsuk, Christopher Conly, Vassilis Athitsos
2014 Proceedings of the 7th International Conference on PErvasive Technologies Related to Assistive Environments - PETRA '14  
In addition to our method that improves sign recognition accuracy, we propose a simple RGB-D alignment tool that can help roughly approximate alignment parameters between the color (RGB) and depth frames  ...  Our results show an improvement over the original work of [14] , achieving an 82% accuracy in ranking signs in the 10 matches.  ...  The rectangles bound various regions, including face and hands. Figure 4 :Figure 5 : 45 Visualization of RGB-D alignment.  ... 
doi:10.1145/2674396.2674421 dblp:conf/petra/JangyodsukCA14 fatcat:5r4qcaysbjdi5hjvzmbygrmfna

Simultaneous Semi-Coupled Dictionary Learning for Matching RGBD Data

Nilotpal Das, Devraj Mandal, Soma Biswas
2016 2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
Extensive experiments on three datasets, EURECOM, VAP RGB-D-T and Texas 3D Face Recognition database show the effectiveness of the proposed framework.  ...  Dictionaries are learnt for the RGB, depth and the canonical data, such that the transformed sparse coefficients of the RGB and the depth data is equal to that of the canonical data.  ...  Rank 1 recognition performance (%) of different algorithms on the Texas 3D Face Recognition database [10] [9] [8] for hidden information scenario RGB-RGB (R-R) and Depth-Depth (D-D) using both SIFT [17  ... 
doi:10.1109/cvprw.2016.37 dblp:conf/cvpr/DasMB16 fatcat:v2qniaoxbjcxnkfonb3jr6id7m


Sasi Kumar Balasundaram, J. Umadevi, B. Sankara Gomathi
This paper aims to achieve the best color face recognition performance.  ...  The effectiveness of color face recognition method has been successfully evaluated by the public face databases.  ...  A learner m t h , is defined as follows: ) ( ) ( ) , ( min max ) ( max , d d d d n X h m n m t    (1) Where m n d ) ( = S(Φm(x), Φm( g x n) ( )) S() is used to measure the distance between two input  ... 
doi:10.24297/ijct.v8i2.3386 fatcat:eg3kexyzezh4reff6v7cg5zfpu

Multi-view Laplacian Eigenmaps Based on Bag-of-Neighbors For RGBD Human Emotion Recognition [article]

Shenglan Liu, Shuai Guo, Hong Qiao, Yang Wang, Bin Wang, Wenbo Luo, Mingming Zhang, Keye Zhang, Bixuan Du
2018 arXiv   pre-print
Human emotion recognition is an important direction in the field of biometric and information forensics. However, most existing human emotion research are based on the single RGB view.  ...  We propose a new supervised nonlinear multi-view laplacian eigenmaps (MvLE) approach and a multihidden-layer out-of-sample network (MHON) for RGB-D humanemotion recognition.  ...  Existing researches on human emotion recognition mainly focus on single view methods, such as physiological signals emotion recognition [1] - [3] , image-based face emotion recognition [4] , [5] ,  ... 
arXiv:1811.03478v1 fatcat:ylt5mmopvvhzva32dfhtyp2neq
« Previous Showing results 1 — 15 out of 15,302 results