Proceedings ArticleDOI
Face recognition for newborns: A preliminary study
Reads0
Chats0
TLDR
The concept of using face recognition for identifying newborns and an automatic face recognition algorithm is introduced and the proposed multiresolution algorithm extracts Speeded up robust features and local binary patterns from different levels of Gaussian pyramid.Abstract:
Newborn swapping and abduction is a global problem and traditional approaches such as ID bracelets and footprinting do not provide the required level of security. This paper introduces the concept of using face recognition for identifying newborns and presents an automatic face recognition algorithm. The proposed multiresolution algorithm extracts Speeded up robust features and local binary patterns from different levels of Gaussian pyramid. The feature descriptors obtained at each Gaussian level are combined using weighted sum rule. On a newborn face database of 34 babies, the proposed algorithm yields rank-1 identification accuracy of 86.9%.read more
Citations
More filters
Proceedings ArticleDOI
A sparse representation approach to face matching across plastic surgery
TL;DR: A novel approach to address the challenges involved in automatic matching of faces across plastic surgery variations is proposed, in which part-wise facial characterization is combined with the recently popular sparse representation approach.
Proceedings ArticleDOI
Face Recognition Algorithm Bias: Performance Differences on Images of Children and Adults
TL;DR: This work identifies the best score-level fusion technique for the child demographic and shows a negative bias for each algorithm on children, further supporting the need for a deeper investigation into algorithm bias as a function of age cohorts.
Proceedings ArticleDOI
Recognizing infants and toddlers using fingerprints: Increasing the vaccination coverage
TL;DR: The following strategies are devised to improve the fingerprint recognition accuracy when comparing the acquired fingerprints against an extended gallery database of 32,768 infant fingerprints collected by VaxTrac in Benin: upsample the acquired fingerprint image to facilitate minutiae extraction, match the query print against templates created from each enrollment impression and fuse the match scores.
Posted Content
Learning Structure and Strength of CNN Filters for Small Sample Size Training
TL;DR: SSF-CNN is proposed which focuses on learning the "structure" and "strength" of filters and significantly reduces the number of parameters required for training while providing high accuracies on the test databases.
Journal ArticleDOI
Domain Specific Learning for Newborn Face Recognition
TL;DR: An autoencoder-based feature representation followed by problem specific distance metric learning via one-shot similarity with one class-online support vector machine is proposed for face recognition of newborn babies.
References
More filters
Journal ArticleDOI
Multiresolution gray-scale and rotation invariant texture classification with local binary patterns
TL;DR: A generalized gray-scale and rotation invariant operator presentation that allows for detecting the "uniform" patterns for any quantization of the angular space and for any spatial resolution and presents a method for combining multiple operators for multiresolution analysis.
Journal ArticleDOI
Robust Real-Time Face Detection
Paul A. Viola,Michael Jones +1 more
TL;DR: In this paper, a face detection framework that is capable of processing images extremely rapidly while achieving high detection rates is described. But the detection performance is limited to 15 frames per second.
Book ChapterDOI
SURF: speeded up robust features
TL;DR: A novel scale- and rotation-invariant interest point detector and descriptor, coined SURF (Speeded Up Robust Features), which approximates or even outperforms previously proposed schemes with respect to repeatability, distinctiveness, and robustness, yet can be computed and compared much faster.
Journal ArticleDOI
Speeded-Up Robust Features (SURF)
TL;DR: A novel scale- and rotation-invariant detector and descriptor, coined SURF (Speeded-Up Robust Features), which approximates or even outperforms previously proposed schemes with respect to repeatability, distinctiveness, and robustness, yet can be computed and compared much faster.
Journal ArticleDOI
Eigenfaces vs. Fisherfaces: recognition using class specific linear projection
TL;DR: A face recognition algorithm which is insensitive to large variation in lighting direction and facial expression is developed, based on Fisher's linear discriminant and produces well separated classes in a low-dimensional subspace, even under severe variations in lighting and facial expressions.