Corpus ID: 86375060

Heterogeneous face recognition

  title={Heterogeneous face recognition},
  author={Anil K. Jain and Brendan Klare},
One of the most difficult challenges in automated face recognition is computing facial similarities between face images acquired in alternate modalities. Called heterogeneous face recognition (HFR), successful solutions to this recognition paradigm would allow the vast collection of face photographs (acquired from driver's licenses, passports, mug shots, and other sources of frontal face images) to be matched against face images from alternate modalities (e.g. forensic sketches, infrared images… 
Robust facial representation for recognition
This thesis investigates both holistic and local feature based representations, and develops several novel representation models in an effort to mitigate within-person variations and enhance discriminative power in face recognition.
Local gradient Gabor pattern (LGGP) with applications in face recognition, cross-spectral matching, and soft biometrics
A novel but simple approach for encoding Gradient information on Gabor-transformed images to represent the face, which can be used for identity, gender and ethnicity assessment and comparable against state-of-the-art descriptor-based approaches in face recognition applications.
A Comprehensive Database for Benchmarking Imaging Systems
The Tufts Face Database is introduced that includes images acquired in various modalities: photograph images, thermal images, near infrared images, a recorded video, a computerized facial sketch, and 3D images of each volunteer's face.
An improved local pattern descriptor for biometrics face encoding: a LC–LBP approach toward face identification
Abstract Local binary pattern (LBP) has proved to be an efficient local image descriptor used in computer vision. LBP operator has successfully been applied in many biometrics applications. Face
Memetic approach for matching sketches with digital face images
An automated algorithm that discriminating information from local regions of both sketches and digital face images is presented, using multi-scale circular Weber's Local descriptor to boost the identification performance.
The CASIA NIR-VIS 2.0 Face Database
The composition of the database, evaluation protocols and baseline performance of PCA on the database are described and two interesting tricks, the facial symmetry and heterogeneous component analysis (HCA) are introduced to improve the performance.
Deep Cross Modal Learning for Caricature Verification and Identification (CaVINet)
This paper presents the first cross modal architecture that handles extreme distortions of caricatures using a deep learning network that learns similar representations across the modalities.
Design of an Efficient Face Recognition Algorithm based on Hybrid Method of Eigen Faces and Gabor Filter
An efficient face recognition algorithm is proposed based on the accuracy of Gabor filter for feature extraction and computing the Eigen faces and efficient compressed feature vector approach is proposed.
Column Flotation of Subbituminous Coal Using the Blend of Trimethyl Pentanediol Derivatives and Pico-Nano Bubbles
Patch-based Ensemble Learning Scheme for Heterogeneous Face Recognition by Cunjian Chen Doctor of Philosophy in Computer Science West Virginia University Arun Ross, Ph.D., Chair The problem of
Modeling Errors in Biometric Surveillance and De-duplication Systems
Modeling Errors in Biometric Surveillance and De-duplication Systems by Brian Matthew DeCann Doctor of Philosophy in Electrical Engineering West Virginia University Arun A. Ross, Ph.D., Chair In


Heterogeneous Face Recognition Using Kernel Prototype Similarities
  • B. Klare, Anil K. Jain
  • Computer Science, Medicine
    IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2013
A generic HFR framework is proposed in which both probe and gallery images are represented in terms of nonlinear similarities to a collection of prototype face images, and Random sampling is introduced into the H FR framework to better handle challenges arising from the small sample size problem.
Age-Invariant Face Recognition
A 3D aging modeling technique is proposed and it is shown how it can be used to compensate for the age variations to improve the face recognition performance.
Coupled Spectral Regression for matching heterogeneous faces
  • Zhen Lei, S. Li
  • Computer Science
    2009 IEEE Conference on Computer Vision and Pattern Recognition
  • 2009
This paper presents a subspace learning framework named Coupled Spectral Regression (CSR) to solve the challenge problem of coupling the two types of face images and matching between them, and shows that the proposed CSR method significantly outperforms the existing methods.
Face Matching and Retrieval Using Soft Biometrics
  • U. Park, Anil K. Jain
  • Computer Science
    IEEE Transactions on Information Forensics and Security
  • 2010
Experimental results show that the use of soft biometric traits is able to improve the face-recognition performance of a state-of-the-art commercial matcher.
Face Photo-Sketch Synthesis and Recognition
This paper is going to study a method for representing face which is based on the features which uses geometric relationship among the facial features like mouth, nose and eyes called Principal Component Analysis followed by Feed Forward Neural Network called PCA-NN.
A Discriminative Model for Age Invariant Face Recognition
This paper proposes a discriminative model to address face matching in the presence of age variation and shows that this approach outperforms a state-of-the-art commercial face recognition engine on two public domain face aging data sets: MORPH and FG-NET.
A biometric database with rotating head videos and hand-drawn face sketches
A new database that includesRotating head videos of 259 subjects; 250 hand-drawn face sketches of 50 subjects; and this is the only currently available database that has a large number of face sketches drawn by multiple artists is described.
Report on the Evaluation of 2D Still-Image Face Recognition Algorithms
This is the first time NIST has reported accuracy of face identification algorithms, and formally supports use of fast search algorithms such as indexing, partitioning and binning to national-size populations.
Illumination Invariant Face Recognition Using Near-Infrared Images
An active near infrared (NIR) imaging system is presented that is able to produce face images of good condition regardless of visible lights in the environment, and it is shown that the resulting face images encode intrinsic information of the face, subject only to a monotonic transform in the gray tone.
3D Model-Based Face Recognition in Video
This work proposes to overcome the pose problem by automatically reconstructing a 3D face model from multiple non-frontal frames in a video, generating a frontal view from the derived 3D model, and using a commercial 2D face recognition engine to recognize the synthesized frontal view.