Filters








6,393 Hits in 5.2 sec

Wide-range, person- and illumination-insensitive head orientation estimation

Ying Wu, K. Toyama
Proceedings Fourth IEEE International Conference on Automatic Face and Gesture Recognition (Cat. No. PR00580)  
Our algorithm handles dramatic changes in illumination, applies to many people without per-user initialization, and covers a wider range (e.g., side and back) of head orientations than previous algorithms  ...  We present an algorithm for estimation of head orientation, given cropped images of a subject's head from any viewpoint.  ...  Acknowledgments: We thank our reviewers and John Krumm for helpful feedback.  ... 
doi:10.1109/afgr.2000.840632 dblp:conf/fgr/WuT00 fatcat:e5zjgmhwsrbohmf7eq72orxp4e

Robust face recognition using 2D and 3D data: Pose and illumination compensation

Sotiris Malassiotis, Michael G. Strintzis
2005 Pattern Recognition  
The paper addresses the problem of face recognition under varying pose and illumination.  ...  Robustness to appearance variations is achieved not only by using a combination of a 2D color and a 3D image of the face, but mainly by using face geometry information to cope with pose and illumination  ...  The result of the above face detection procedure is an estimate of the center and orientation of the 3D blob corresponding to the head, which may be used to define an oriented bounding box on the image  ... 
doi:10.1016/j.patcog.2005.02.001 fatcat:hca26urhybejhbnckvrxpuzy6m

Estimating Head Orientation Using a Combination of Multiple Cues

Bima Sena Bayu DEWANTARA, Jun MIURA
2016 IEICE transactions on information and systems  
This paper proposes an appearance-based novel descriptor for estimating head orientation.  ...  Also, we can extend the proposed method by combining it with a head detection and tracking system to enable it to estimate human head orientation in real applications.  ...  Miss-orientation estimation (#159) occurs due to a severe illumination, while false positive detections of the human upper body and miss-orientation estimation (#387) occur due to an ambient light and  ... 
doi:10.1587/transinf.2015edp7375 fatcat:aojsakkkcvbjlch5iplspyirli

Fast, reliable head tracking under varying illumination: an approach based on registration of texture-mapped 3D models

M. La Cascia, S. Sclaroff, V. Athitsos
2000 IEEE Transactions on Pattern Analysis and Machine Intelligence  
An improved technique for 3D head tracking under varying illumination conditions is proposed. The head is modeled as a texture mapped cylinder.  ...  To solve the registration problem in the presence of lighting variation and head motion, the residual error of registration is modeled as a linear combination of texture warping templates and orthogonal  ...  For a wide range of values of this parameter performance is illumination, as described in the text.  ... 
doi:10.1109/34.845375 fatcat:ltwzadlbgjaqpdvyfueo7h4ppy

A 2D+3D face authentication system robust under pose and illumination variations

F. Tsalakanidou, S. Malassiotis, M.G. Strintzis
2005 Image and Signal Processing and Analysis  
Depth information, acquired by a novel low-cost 3D and color sensor based on the structured light approach, is used for robust face detection, localization and 3D pose estimation.  ...  Illumination compensation exploits depth data to recover the illumination of the scene and relight the image under frontal lighting.  ...  and head rotations [20] .  ... 
doi:10.1109/ispa.2005.195410 fatcat:5woil3xowjgtlavt6z7ifrstfa

Illumination Processing in Face Recognition [chapter]

Yongping Li, Chao Wang, Xinyu Ao
2010 Face Recognition  
If this notation is adopted, a dramatic performance improvement (a) Global illumination (b) Local illumination www.intechopen.com would be offered to a wide range of filters and different baseline matching  ...  Generation of illumination direction map For the same person, the value of β is greatly different with illumination orientation variations; for different persons, the value of β is similar with the same  ...  Also a broad range of problems is covered: feature extraction and dimensionality reduction (chapters 1-4), 2D face recognition from the point of view of full system proposal (chapters 5-10), illumination  ... 
doi:10.5772/8937 fatcat:75e3tf6sd5ep3byewjbt2tnx4u

ILLUMINATION PROCESSING IN FACE RECOGNITION

ZHENXUE CHEN, CHENGYUN LIU, FALIANG CHANG, XUZHEN HAN, KAIFANG WANG
2014 International journal of pattern recognition and artificial intelligence  
If this notation is adopted, a dramatic performance improvement (a) Global illumination (b) Local illumination www.intechopen.com Face Recognition 202 would be offered to a wide range of filters and  ...  Generation of illumination direction map For the same person, the value of β is greatly different with illumination orientation variations; for different persons, the value of β is similar with the same  ...  Also a broad range of problems is covered: feature extraction and dimensionality reduction (chapters 1-4), 2D face recognition from the point of view of full system proposal (chapters 5-10), illumination  ... 
doi:10.1142/s0218001414560114 fatcat:ifk7ftontzgrdkz4pe7jjdkuoa

Face Recognition and Pose Estimation with Parametric Linear Subspaces [chapter]

Kazunori Okada, Christoph von der Malsburg
2008 Studies in Computational Intelligence  
The results demonstrated sub-degree pose estimation and sub-pixel shape synthesis accuracy, as well as high degree of generalization to unseen head poses within ±50 degree range of full 3D head rotation  ...  A novel pose-insensitive face recognition framework is also proposed by exploiting the PPLS model to represent each known person.  ...  Acknowledgments The authors thank Shigeru Akamatsu and Katsunori Isono for making their 3D face database available for this study. This study was partially supported by ONR grant N00014-98-1-0242.  ... 
doi:10.1007/978-3-540-76831-9_3 fatcat:lkn3mgastbb4bgwztkboc5rowe

Model-based enhancement of lighting conditions in image sequences

Peter Eisert, Bernd Girod, C.-C. Jay Kuo
2002 Visual Communications and Image Processing 2002  
To provide the estimator with surface normal information, the objects in the scene are represented by 3-D shape models and their motion and deformation are tracked over time using a model-based estimation  ...  The efficiency and robustness of these algorithms can be significantly improved by removing the undesired effects of changing illumination.  ...  Position, orientation, and facial expressions are estimated and the head model is moved and deformed appropriately to match the original frame [10] .  ... 
doi:10.1117/12.453065 fatcat:byrigltlffafpjiwntxflurl2m

Age and Gender Estimation Using Global and Local Features with AAM and LGDPHS

Atsushi Higashi, Yohei Fukumizu, Tomonori Izumi, Hironori Yamauchi
2012 The Journal of the Institute of Image Electronics Engineers of Japan  
Recently, services using facial information such as age and gender are provided widely. This paper proposes a mean to estimate age and gender at once in facial images by using novel features.  ...  Next, the global and local features are combined to one vector. Finally, age is estimated by using SVM and SVR, and also gender is classified by using SVM.  ...  Since, the LGDP is insensitive to environmental noise and illumination variations, extracts robust facial feature.  ... 
doi:10.11371/iieej.41.262 fatcat:5w34nwus3rg5bdisdwoqivh5e4

Single-shot three-dimensional imaging with a metasurface depth camera [article]

Shane Colburn, Arka Majumdar
2019 arXiv   pre-print
We demonstrate the first visible wavelength and polarization-insensitive metasurface depth camera, representing a significant form factor reduction for such systems.  ...  By decoding the captured data in software, our system produces a fully reconstructed image and transverse depth map of three-dimensional scenes with a fractional ranging error of 1.7%.  ...  fidelity over a wide depth range 32 .  ... 
arXiv:1910.12111v1 fatcat:izrta7wl5vg6tisi7efdbdmw7i

Eye Tracking and ROI Detection within a Computer Screen Using a Monocular Camera

Guangmin Sun, Junjie Zhang, Kun Zheng, Xiaohui Fu
2020 Journal of Web Engineering  
The results show that the method achieves an average error of 1.85∘ with head fixed and 3.58∘ with head movement in the range of −45∘ and 45∘.  ...  Experiments were performed to evaluate the face detection, landmarks, iris detection, eye movement estimation, and head pose estimation on databases such as the Hong Kong, BioID, and Boston University  ...  For example, Sun and Yin propose a head pose estimation method based on 3D facial models [6] . Symmetry plane was used to estimate the pose orientation.  ... 
doi:10.13052/jwe1540-9589.19789 fatcat:apa2tpf7urdfngo4u7wltbzcfe

Hybrid Eye-Tracking on a Smartphone with CNN Feature Extraction and an Infrared 3D Model

Braiden Brousseau, Jonathan Rose, Moshe Eizenman
2020 Sensors  
Our system uses a 3D gaze-estimation model that enables accurate point-of-gaze (PoG) estimation with free head and device motion.  ...  on smartphones that use natural illumination and machine-learning techniques to estimate the PoG.  ...  Acknowledgments: Both a prototype infrared smartphone and a research grant which enabled this work was provided by Huawei Technologies Co., Ltd.  ... 
doi:10.3390/s20020543 pmid:31963823 pmcid:PMC7014547 fatcat:tdohdrftvvavbhbucp4woxsz3m

Dense 3D face alignment from 2D video for real-time use

László A. Jeni, Jeffrey F. Cohn, Takeo Kanade
2017 Image and Vision Computing  
Because no assumptions are required about illumination or surface properties, the method can be applied to a wide range of imaging conditions that include 2D video and uncalibrated multi-view video.  ...  The method has been validated in a battery of experiments that evaluate its precision of 3D reconstruction, extension to multi-view reconstruction, temporal integration for videos and 3D head-pose estimation  ...  A small sample-set that covers a wide head-pose range will yield to smaller reconstruction error.  ... 
doi:10.1016/j.imavis.2016.05.009 pmid:29731533 pmcid:PMC5931713 fatcat:pue3aqhrdbdwhkv75agk2pdody

Head yaw estimation via symmetry of regions

Bingpeng Ma, Annan Li, Xiujuan Chai, Shiguang Shan
2013 2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG)  
Ahstract-This paper proposes a novel method to estimate the head yaw rotations using the symmetry of regions.  ...  We argue and reveal that the symmetry between the two regions in the same horizontal row are closely relevant to the yaw rotation of head, while at the same time insensitive to the identity of the face  ...  Since this decrease of the symmetry is insensitive to the identity of the input face, it can be applied to estimate the head pose.  ... 
doi:10.1109/fg.2013.6553726 dblp:conf/fgr/MaLCS13 fatcat:siigkt6rcrhnperomzcar3nypa
« Previous Showing results 1 — 15 out of 6,393 results