354 Hits in 3.7 sec

Face recognition at a distance system for surveillance applications

Frederick W. Wheeler, Richard L. Weiss, Peter H. Tu
2010 2010 Fourth IEEE International Conference on Biometrics: Theory, Applications and Systems (BTAS)  
This remote biometric collection and identification problem can be addressed with an active vision system where people are detected and tracked with wide-field-of-view cameras and near-field-of-view pan-tilt-zoom  ...  The system features predictive subject targeting and an adaptive target selection mechanism based on the current actions and history of each tracked subject to help ensure that facial images are captured  ...  A detected face is cropped from the full frame image and passed asynchronously to the face recognition manager.  ... 
doi:10.1109/btas.2010.5634523 dblp:conf/btas/WheelerWT10 fatcat:rsbqcln7ynh4hfzimo35ppoqsy

Deep Learning Models for Automatic Makeup Detection

Theiab Alzahrani, Baidaa Al-Bander, Waleed Al-Nuaimy
2021 AI  
Makeup can disguise facial features, which results in degradation in the performance of many facial-related analysis systems, including face recognition, facial landmark characterisation, aesthetic quantification  ...  In this work, we conduct a comparative study and design automated facial makeup detection systems leveraging multiple learning schemes from a single unconstrained photograph.  ...  All the detected and cropped faces are then resized into 128 × 128 × 3 and normalised.  ... 
doi:10.3390/ai2040031 doaj:23804649723344e88e534b0a7537bbf9 fatcat:jwlbcgfhlncbfd4dxxce2ahmku

Automatic Facial Aging/Rejuvenating Synthesis Method

Ching Tang Hsieh, Chia Shing Hu, Chun Wei Pan
2013 Applied Mechanics and Materials  
First, we use AdaBoost and ASM algorithm to extract the feature set of human face, and rectify them by the concept of facial geometric invariance.  ...  At present, the synthesizing faces of different ages does not emphasize on feature alignment and rectification of twisted images.  ...  The width and height of the face area are calculated based on the locations of the landmarks . The face area is then cropped out, as shown in Figure 5 .  ... 
doi:10.4028/ fatcat:rso5ncd22rgdlnqbofh46lzmem

Computer vision based eyewear selector

Oscar Déniz, Modesto Castrillón, Javier Lorenzo, Luis Antón, Mario Hernandez, Gloria Bueno
2010 Journal of Zhejiang University SCIENCE C  
The system also includes a face and eye detection module and a glasses management module.  ...  This is achieved by using a camera with motorized zoom, iris, white balance, etc. This feature can be specially useful in environments with changing illumination and shadows, like in an optical shop.  ...  Cayetano Guerra and J. Tomás Milán for providing the glasses models.  ... 
doi:10.1631/jzus.c0910377 fatcat:ynkch7b24vcepogqs5o2umdh6e

Unsupervised Discovery of Object Landmarks as Structural Representations [article]

Yuting Zhang, Yijie Guo, Yixin Jin, Yijun Luo, Zhiyuan He, Honglak Lee
2018 arXiv   pre-print
The coordinates of our landmarks are also complementary features to pretrained deep-neural-network representations in recognizing visual attributes.  ...  Our discovered landmarks are semantically meaningful and more predictive of manually annotated landmarks than those discovered by previous methods.  ...  Acknowledgements This work was supported in part by ONR N00014-13-1-0762, NSF CAREER IIS-1453651, and Sloan Research Fellowship.  ... 
arXiv:1804.04412v1 fatcat:cabwrmgygfb2ti6hm3cw6wepam

A simple automatic facial aging/rejuvenating synthesis method

Ching-Tang Hsieh, Chun-Wei Pan, Chia-Shing Hu
2011 2011 IEEE International Conference on Systems, Man, and Cybernetics  
First, we use AdaBoost and ASM algorithm to extract the feature set of human face, and rectify them by the concept of facial geometric invariance.  ...  At present, the synthesizing faces of different ages does not emphasize on feature alignment and rectification of twisted images.  ...  The Gabor wavelet is mainly used in face recognition systems to capture frequency information from facial features [5] [7] [9] [10] [11] .  ... 
doi:10.1109/icsmc.2011.6084154 dblp:conf/smc/HsiehPH11 fatcat:fvod7txfazdmld3nldsoosattq

Multi-task Learning of Facial Landmarks and Expression

Terrance Devries, Kumar Biswaranjan, Graham W. Taylor
2014 2014 Canadian Conference on Computer and Robot Vision  
We show competitive results on two large-scale datasets, the ICML 2013 Facial Expression Recognition challenge, and the Toronto Face Database.  ...  In this paper we demonstrate that learning representations to predict the position and shape of facial landmarks can improve expression recognition from images.  ...  From left to right: a) a face from the ICML dataset and its 68 facial landmarks obtained using [12] .  ... 
doi:10.1109/crv.2014.21 dblp:conf/crv/DevriesBT14 fatcat:t4m7qve7ivb7rewvqmiyio565q

Recognized Face Tracking for CONBE Robot

Sakmongkon Chumkamon, Eiji Hayashi
2014 Journal of Robotics, Networking and Artificial Life (JRNAL)  
In this paper, we experiment and present the results of the face recognition system and the tracking control system such as the tracking error and time.  ...  In this paper we present the basis system in the CONBE robot that consist of the two main sections as the face recognition and robot gaze tracking.  ...  Masato Koike from Department of Mechanical Information Science and Technology, Kyushu Institute of technology who contributed the sample source code for the robot eye expression.  ... 
doi:10.2991/jrnal.2014.1.2.9 fatcat:7wubccihwnfzbiqela767xkjha

LARNet: Real-Time Detection of Facial Micro Expression Using Lossless Attention Residual Network

Mohammad Farukh Hashmi, B. Kiran Kumar Ashish, Vivek Sharma, Avinash G. Keskar, Neeraj Dhanraj Bokde, Jin Hee Yoon, Zong Woo Geem
2021 Sensors  
However, the spatial and temporal information extracted from the face is encoded in LARNet for a feature fusion extraction on specific crucial locations, such as nose, cheeks, mouth, and eyes regions.  ...  However, the main research is to provide an analysis of the specific parts that are crucial for detecting the micro expressions from a face.  ...  The authors have used 128 landmarks to detect the face [47] and cropped the face when the data were captured with zoom out settings.  ... 
doi:10.3390/s21041098 pmid:33562767 fatcat:fsyjbl25jnbwrerxlgn3k6xoey

FaceEraser: Removing Facial Parts for Augmented Reality [article]

Miao Hua, Lijie Liu, Ziyang Cheng, Qian He, Bingchuan Li, Zili Yi
2021 arXiv   pre-print
Our task is to remove all facial parts (e.g., eyebrows, eyes, mouth and nose), and then impose visual elements onto the "blank" face for augmented reality.  ...  Finally, we demonstrate various face-oriented augmented reality applications on top of our facial parts removal model.  ...  Facial analysis We use a face detection model to discover faces from wild images. 106 facial key points [13] are detected and used to align faces, locate facial parts and generate facial masks, which  ... 
arXiv:2109.10760v2 fatcat:j6vztdtb6bdxtnthufwbxe2dbq

Swapped face detection using deep learning and subjective assessment

Xinyi Ding, Zohreh Raziei, Eric C. Larson, Eli V. Olinick, Paul Krueger, Michael Hahsler
2020 EURASIP Journal on Information Security  
Distinguished from existing methods that only provide detection accuracy, we also provide uncertainty for each prediction, which is critical for trust in the deployment of such detection systems.  ...  In this study, we use deep transfer learning for face swapping detection, showing true positive rates greater than 96% with very few false alarms.  ...  Thus, it may require the model to learn more subtle features, such as looking for changes in lighting condition near the cropped face or stretching of facial landmarks to align the perspectives.  ... 
doi:10.1186/s13635-020-00109-8 fatcat:d355c7jm4zfppjjrwksatv4loq

Bayesian Network Enhanced Prediction for Multiple Facial Feature Tracking

Li Huang, Congyong Su
2005 ELCVIA Electronic Letters on Computer Vision and Image Analysis  
In the prediction model, CAMSHIFT is used to track the face in video in advance, and facial features' spatial constraint is utilized to roughly obtain the positions of facial features.  ...  It is challenging to track multiple facial features simultaneously in video while rich facial expressions are presented in a human face.  ...  (c) Edge detection result for image sequence. Figure 11 : 11 Comparison of tracking results: from far to near, quickly approaching the camera, and with head orientation and face expression.  ... 
doi:10.5565/rev/elcvia.114 fatcat:j4uhp4ek55bhfbxywic5w7nki4

DeepUAge: Improving Underage Age Estimation Accuracy to Aid CSEM Investigation

Felix Anda, Nhien-An Le-Khac, Mark Scanlon
2020 Forensic Science International: Digital Investigation  
An evaluation, validation and comparison of the proposed model is performed against existing facial age classifiers resulting in the best overall performance for underage subjects.  ...  This paper describes the design and implementation of this model.  ...  Acknowledgements The authors wish to acknowledge the contribution of colleagues in the UCD Forensics and Security Research Group and in the MITRE Corporation in the curation of the VisAGe dataset.  ... 
doi:10.1016/j.fsidi.2020.300921 fatcat:fkl6oz7acfb4xc2kcp2zzgieba

In-plane Rotational Alignment of Faces by Eye and Eye-pair Detection

M. F. Karaaba, O. Surinta, L. R. B. Schomaker, M. A. Wiering
2015 Proceedings of the 10th International Conference on Computer Vision Theory and Applications  
In-plane Rotational Alignment of Faces by Eye and Eye-pair Detection.  ...  Two feature extraction methods, the restricted Boltzmann machine and the histogram of oriented gradients, are compared to extract feature vectors from a sliding window.  ...  Although the faces in the images we collected are in different zoom levels, we kept the face-to-image zoom ratio always bigger than 0.5 during cropping.  ... 
doi:10.5220/0005308303920399 dblp:conf/visapp/KaraabaSSW15 fatcat:733fij7j5vdafc7aq6r2wpj3ca

Race Recognition Using Deep Convolutional Neural Networks

Thanh Vo, Trang Nguyen, C. Le
2018 Symmetry  
An efficient Race Recognition Framework (RRF) is proposed that includes information collector (IC), face detection and preprocessing (FD&P), and RR modules.  ...  to compare the accuracy between RR-CNN and RR-VGG.  ...  combines features from both 2D and 3D information, or the fusion of face and gait, etc.  ... 
doi:10.3390/sym10110564 fatcat:bajqx34s4vc4domly7x7ywa3ue
« Previous Showing results 1 — 15 out of 354 results