Proceedings ArticleDOI
Person Authentication Using Head Images
Aakarsh Malhotra,Richa Singh,Mayank Vatsa,Vishal M. Patel +3 more
- pp 409-417
TLDR
The experiments suggest that head images can be effectively used to ascertain human identity and the availability of this database could pave further research in this field.Abstract:
In many surveillance applications, the cameras are placed at overhead heights for human identification. In such real-world scenarios, the person of interest might be walking away from the camera and the only information available is "image of the person's head". In this research, we investigate the usage of head images for person recognition and propose it as a soft-biometric modality. With its viability for human recognition, application of head images can also be extended with other face recognition algorithms for surveillance. We propose a head image database pertaining to 103 subjects with more than 600 images. In addition to the database, we propose a framework for head image-based person verification. As a pre-processing stage, the framework includes evaluation of two segmentation algorithms. We also perform benchmarking evaluations of various texture, key-point, and learning-based representation algorithms and establish the baseline results. The experiments suggest that head images can be effectively used to ascertain human identity and the availability of this database could pave further research in this field.read more
Citations
More filters
Soft-biometrics : unconstrained authentication in a surveillance environment
TL;DR: In this paper, the authors proposed three part (head, torso, legs) height and colour soft biometric models, and demonstrate their verification performance on a subset of the PETS 2006 database.
Journal ArticleDOI
Robust Head Detection in Complex Videos Using Two-Stage Deep Convolution Framework
TL;DR: This paper presents a two-stage head detection framework that utilizes fully convolutional network (FCN) to generate scale-aware proposals followed by CNN that classifies each proposal into two classes, i.e. head and background.
Proceedings ArticleDOI
Which Body Is Mine
TL;DR: A dual-pathway framework which computes head and body discriminating features independently, and learns the correlation between such features, and achieves promising experimental results on small and challenging datasets.
References
More filters
Proceedings ArticleDOI
Vision-based overhead view person recognition
TL;DR: A framework, which tries to solve the person recognition problem using the top view of the person by making use of DTC and Bayesian networks the output of the various sensors can be combined to solve this problem.
Journal ArticleDOI
Soft Biometrics: Globally Coherent Solutions for Hair Segmentation and Style Recognition Based on Hierarchical MRFs
Hugo Proença,Joao C. Neves +1 more
TL;DR: A multi-layered (hierarchical) architecture for MRFs that is based exclusively in pairwise connections and typically produces globally coherent solutions, which is particularly suitable for problems that deal with biological data (e.g., biometrics), where the reasonability of the solutions can be objectively measured.
Proceedings ArticleDOI
A density based method for automatic hairstyle discovery and recognition
TL;DR: This paper proposes automated approach for generation of hair, background and face-skin probability-masks for different hairstyle category without requiring manual annotation and uses Agglomerative clustering for automatic discovery of distinct hairstyles.
Proceedings ArticleDOI
Human Hair Segmentation and Length Detection for Human Appearance Model
TL;DR: The detected human hair length can be used as an invariant feature to be embedded into a human appearance model which can be employed for human detection, indexing and searching in multi cameras network system.
Proceedings ArticleDOI
Hair style retrieval by semantic mapping on informative patches
Nan Wang,Haizhou Ai +1 more
TL;DR: To bridge the “semantic gap” between low-level features and high-level hairstyle, a mapping function is incorporated which integrates local and pairwise evidences in MRF framework and a RankBoost learning algorithm is proposed to select the most informative patches integrating the heuristic information of mapping function accuracy.
Related Papers (5)
A real-time person tracking system based on SiamMask network for intelligent video surveillance
Imran Ahmed,Gwanggil Jeon +1 more