Partially-supervised learning from facial trajectories for face recognition in video surveillance

De-la-Torre, Miguel; Granger, Éric; Radtke, Paulo V. W.; Sabourin, Robert; Gorodnichy, Dmitry O.

doi:10.1016/j.inffus.2014.05.006

Cited by 63 publications

(41 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…update-threshold to each matching score to select ROI patterns to update the corresponding gallery-facemodel [9,14]. The co-update techniques seek corroboration of scores from two or more matchers, typically on multiple traits (e.g., face and finger prints) for cross-updating [25,26].…”

Section: Adaptive Face Modelingmentioning

confidence: 99%

“…In [14], a learn-and-combine strategy is employed for spatiotemporal FR in VS. When the number of positive ensemble predictions surpasses a higher update threshold, then all target samples from the trajectory are combined with non-target samples (selected from the cohort and universal models) to update the corresponding face model.…”

Section: Spatiotemporal Fusionmentioning

confidence: 99%

“…Table 2 gives an overview of the experiments presented in Section 5. Illustration of trajectory-level analysis used to evaluate the overall performance of a system for still-to-video FR over one video [14].…”

Section: Performance Measuresmentioning

confidence: 99%

“…If an accumulated score for a trajectory surpasses a individual-specific decision threshold, the corresponding individual of interest is considered to be detected. This trajectory-based analysis is typically used by the surveillance system to reduce ambiguity in video-based FR [14].…”

mentioning

confidence: 99%

See 3 more Smart Citations

Adaptive appearance model tracking for still-to-video face recognition

Dewan

Granger

Marcialis

et al. 2016

Pattern Recognition

View full text Add to dashboard Cite

Systems for still-to-video face recognition (FR) seek to detect the presence of target individuals based on reference facial still images or mug-shots. These systems encounter several challenges in video surveillance applications due to variations in capture conditions (e.g., pose, scale, illumination, blur and expression) and to camera inter-operability. Beyond these issues, few reference stills are available during enrollment to design representative facial models of target individuals. Systems for still-to-video FR must therefore rely on adaptation, multiple face representation, or synthetic generation of reference stills to enhance the intra-class variability of face models. Moreover, many FR systems only match high quality faces captured in video, which further reduces the probability of detecting target individuals. Instead of matching faces captured through segmentation to reference stills, this paper exploits Adaptive Appearance Model Tracking (AAMT) to gradually learn a track-face-model for each individual appearing in the scene. The Sequential Karhunen-Loeve technique is used for online learning of these track-face-models within a particle filter-based face tracker. Meanwhile, these models are matched over successive frames against the reference still images of each target individual enrolled to the system, and then matching scores are accumulated over several frames for robust spatiotemporal recognition. A target individual is recognized if scores accumulated for a track-face-model over a fixed time surpass some decision threshold. The main advantage of AAMT over traditional still-to-video FR systems is the greater diversity of facial representation that may be captured during operations, and this can lead to better discrimination for spatiotemporal recognition. Compared to state-of-the-art adaptive biometric systems, the proposed method selects facial captures to update an individual's face model more reliably because it relies on information from tracking. Simulation results obtained with the Chokepoint video dataset indicate that the proposed method provides a significantly higher level of performance compared state-of-the-art systems when a single reference still per individual is available for matching. This higher level of performance is achieved when the diverse facial appearances that are captured in video through AAMT correspond to that of reference stills.

show abstract

Section: Adaptive Face Modelingmentioning

confidence: 99%

Section: Spatiotemporal Fusionmentioning

confidence: 99%

Section: Performance Measuresmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Adaptive appearance model tracking for still-to-video face recognition

Dewan

Granger

Marcialis

et al. 2016

Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…In addition, ensembles of these binary classifiers per individual of interest have been successfully applied to face re-identification [Radtke et al, 2014, De-la Torre et al, 2015a, De-la Torre et al, 2015b. In order to define an accurate decision boundary, a one-class classifier requires a large number of representative target samples which is not often feasible in practice.…”

Section: Introductionmentioning

confidence: 99%

Classifier Ensembles with Trajectory Under-Sampling for Face Re-Identification

Soleymani

Granger

Fumera

2016

Proceedings of the 5th International Conference on Pattern Recognition Applications and Methods

Self Cite

View full text Add to dashboard Cite

Abstract:In person re-identification applications, an individual of interest may be covertly tracked and recognized based on trajectories of faces or other distinguishing information captured with video surveillance camera. However, a varying level of imbalance often exists between target and non-target facial captures, and this imbalance level may differ from what was considered during design. The performance of face classification systems typically declines in such cases because, to avoid bias towards the majority class (non-target), they tend to optimize the overall accuracy under a balance class assumption. Specialized classifier ensembles trained on balanced data, where non-target samples are selected through random under-sampling or cluster-based sampling, have been proposed in literature, but they suffer from loss of information and low diversity and accuracy. In this paper, a new ensemble method is proposed for generating a diverse pool of classifiers, each one trained on different levels of class imbalance and complexity for a greater diversity of opinion. Ensembles with Trajectory Under Sampling (EoC-TUS) allows to select subsets of non-target training data based on trajectories information. Variants of these ensembles can give more importance to the most efficient classifiers in identifying target samples, or define efficient and diverse decision boundaries by starting selection of trajectories from the farthest ones to the target class. For validation, experiments are conducted using videos captured in the Faces In Action dataset, and compared to several baseline techniques. The proposed EoC-TUS outperforms state-of-the-art techniques in terms of accuracy and diversity over a range of imbalance levels in the input video.

show abstract

Principal component analysis, hidden Markov model, and artificial neural network inspired techniques to recognize faces

Aggarwal¹,

Alshehri

Kumar

et al. 2020

Concurrency and Computation

View full text Add to dashboard Cite

Face Recognition is a challenging task for recognizing and detecting the identity of an individual. Although, plethora of work has already been done in the field of pattern recognition still there has been lot which has not been addressed in any of the literature. In the current research, we have presented a comparative analysis using three popularly known techniques for face recognition namely, Principal Components Analysis (PCA) using Eigen Faces, Hidden Markov Model (HMM) using Singular Value Decomposition, and Artificial Neural Network (ANN) using Gabor filters. These techniques are implemented and evaluated using various measuring metrics such as false acceptance, false recognition rate, and so on. We used ORL and Yale Face dataset to test the robustness of implemented algorithms. Results show that ANN model for face recognition outperforms the other two techniques by achieving more accurate results and shows the highest recognition rate of 97.49% on ORL database. Moreover, it is also observed that ANN model shows the minimum error count of about 2.502% on ORL database while it is 3.5% on Yale Face dataset. To evaluate further, the implemented techniques are compared with best known techniques in class implemented by various researchers.

show abstract

Partially-supervised learning from facial trajectories for face recognition in video surveillance

Cited by 63 publications

References 36 publications

Adaptive appearance model tracking for still-to-video face recognition

Adaptive appearance model tracking for still-to-video face recognition

Classifier Ensembles with Trajectory Under-Sampling for Face Re-Identification

Principal component analysis, hidden Markov model, and artificial neural network inspired techniques to recognize faces

Contact Info

Product

Resources

About