Proceedings ArticleDOI
Matching age separated composite sketches and digital face images
Tarang Chugh,Himanshu Bhatt,Richa Singh,Mayank Vatsa +3 more
- pp 1-6
TLDR
The results on a large gallery experiment suggest that the proposed algorithm efficiently encodes discriminative information from local facial regions useful for matching composite sketches with age separated digital face images.Abstract:Â
Matching sketches with digital face images is one of the highly sought face recognition applications. An important aspect, though less explored till now, is matching age separated sketches with digital face images. Several law enforcement agencies are progressively using composite sketches for apprehending individuals. This research proposes an algorithm for matching composite sketches with digital face images across different age. It extracts discriminative shape, orientation, and texture features from local regions of a face using image moments and histogram of oriented gradients. The complementary information from these two features is further combined at match score level for efficiently matching composite sketches with digital face images across different age. To study the effects of age variations, this research also presents a composite sketch database with age separated sketches and digital face images. The results on a large gallery experiment suggest that the proposed algorithm efficiently encodes discriminative information from local facial regions useful for matching composite sketches with age separated digital face images.read more
Citations
More filters
Journal ArticleDOI
A survey on heterogeneous face recognition
TL;DR: This survey provides a comprehensive review of established techniques and recent developments in HFR, and offers a detailed account of datasets and benchmarks commonly used for evaluation.
Proceedings ArticleDOI
Composite sketch recognition via deep network - a transfer learning approach
TL;DR: In the proposed algorithm, first the deep learning architecture based facial representation is learned using large face database of photos and then the representation is updated using small problem-specific training database.
Proceedings ArticleDOI
Recognizing composite sketches with digital face images via SSD dictionary
TL;DR: The proposed algorithm utilizes a SSD based dictionary generated via 50,000 images from the CMU Multi-PIE database, and the gallery-probe feature vectors created using SSD dictionary are matched using GentleBoostKO classifier.
Journal ArticleDOI
Composite sketch recognition using saliency and attribute feedback
TL;DR: The results obtained show that the proposed algorithm improves the state-of-art in matching composite sketch and digital face images and yields the rank 50 identification accuracy of 70.3% on a database of 1500 subjects.
Proceedings ArticleDOI
Face Sketch Matching via Coupled Deep Transform Learning
TL;DR: DeepTransformer as mentioned in this paper learns a transformation and mapping function between the features of two domains, which can be applied with any existing learned or hand-crafted feature and can be used for sketch-to-sketch matching.
References
More filters
Proceedings ArticleDOI
Histograms of oriented gradients for human detection
Navneet Dalal,Bill Triggs +1 more
TL;DR: It is shown experimentally that grids of histograms of oriented gradient (HOG) descriptors significantly outperform existing feature sets for human detection, and the influence of each stage of the computation on performance is studied.
Journal ArticleDOI
Visual pattern recognition by moment invariants
TL;DR: It is shown that recognition of geometrical patterns and alphabetical characters independently of position, size and orientation can be accomplished and it is indicated that generalization is possible to include invariance with parallel projection.
Journal ArticleDOI
Information fusion in biometrics
Arun Ross,Anil K. Jain +1 more
TL;DR: This paper addresses the problem of information fusion in biometric verification systems by combining information at the matching score level by combining three biometric modalities (face, fingerprint and hand geometry).
Book ChapterDOI
Information Fusion in Biometrics
TL;DR: This paper addresses the problem of information fusion in verification systems and experimental results on combining three biometric modalities (face, fingerprint and hand geometry) are presented.
Journal ArticleDOI
Age-Invariant Face Recognition
TL;DR: 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.