Double Trouble: Differentiating Identical Twins by Face Recognition

Paone, Jeffrey R.; Flynn, Patrick J.; Philips, P. Jonathon; Bowyer, Kevin W.; Bruegge, Richard W. Vorder; Grother, Patrick J.; Quinn, George; Pruitt, Matthew T.; Grant, Jason M.

doi:10.1109/tifs.2013.2296373

Cited by 33 publications

(15 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this paper, we collect a new unconstrained face dataset which contains 455 pairs of identical twins to form negative face pairs with quite similar appearance for the challenging fine-grained unconstrained face verification, as well as develop a benchmark protocol for evaluating several baseline verification approaches for this problem. Different from the works [20,18,11,17] in distinguishing between identical twins by face recognition under controlled conditions, we aim to determine whether a face pair depicts the same person or not in the scenario that two images in each negative pairs are very similar in appearance. To our best knowledge, this is the first study on the problem of fine-grained face verification in the wild.…”

Section: Positive Pairsmentioning

confidence: 99%

Fine-grained face verification: Dataset and baseline results

Tan

2015

2015 International Conference on Biometrics (ICB)

View full text Add to dashboard Cite

This paper investigates the problem of fine-grained face verification under unconstrained conditions. For the conventional face verification task, the verification model is trained with some positive and negative face pairs, where each positive sample pair contains two face images of the same person while each negative sample pair usually consists of two face images from different subjects. However, in many real applications, facial appearance of the twins looks very similar even if they are considered as a negative pair in face verification. Therefore, it is important to differentiate a given face pair to determine whether it is from the same person or a twins for a practical face verification system because most existing face verification systems fails to work well in such a scenario. In this work, we define the problem as fine-grained face verification and collect an unconstrained face dataset which contains 455 pairs of identical twins to generate negative face pairs to evaluate several baseline verification models for fine-grained unconstrained face verification. Benchmark results on the unsupervised setting and restricted setting show the challenge of the finegrained face verification in the wild.978-1-4799-7824-3/15/$31.00 ©2015 IEEE

show abstract

Section: Positive Pairsmentioning

confidence: 99%

Fine-grained face verification: Dataset and baseline results

Tan

2015

2015 International Conference on Biometrics (ICB)

View full text Add to dashboard Cite

show abstract

“…For faces, when images are taken in mobile studios in the same collection session, it is possible to distinguish twins; however, when face images are taken a year apart, it is an extremely challenging problem [23]. Twins do have similarity of iris texture, but it is not a similarity that is seen in matching iris codes.…”

Section: B Scientific Knowledge and Technical Advancementmentioning

confidence: 99%

Lessons from collecting a million biometric samples

Flynn

Bowyer

Phillips

2015

2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG)

Self Cite

View full text Add to dashboard Cite

Over the past decade, independent evaluations have become commonplace in many areas of experimental computer science, including face and gesture recognition. A key attribute of many successful independent evaluations is a curated data set. Desired things associated with these data sets include appropriateness to the experimental design, a corpus size large enough to allow statistically rigorous characterization of results, and the availability of comprehensive metadata that allow inferences to be made on various data set attributes. In this paper, we review a ten-year biometric sampling effort that enabled the creation of several key biometrics challenge problems. We summarize the design and execution of data collections, identify key challenges, and convey some lessons learned.

show abstract

“…Further, among the past works on identical twins' identification or verification with the application of the Unimodal biometric system include: Wonder Ears, which employs images of ears to identify identical twins (Nejati et al, 2012), new multimodal database from the biometric traits of twins (Hamid and Faez, 2013). Discriminability between the fingerprints of twins (Jain et al, 2001), DNA analysis (Jain et al, 2002), computational discriminability analysis on the fingerprints of twins (Liu and Srihari, 2009), '3D Face Recognition' method to recognize the face of identical twins (Vipin et al, 2011), facial marks analysis to differentiate identical twins (Srinivas et al, 2012), 'Double Trouble' method for recognising identical twins' by face (Paone et al, 2014). However, Muhammed and Shamsuddin (2012) opined that all these studies were physiological in nature which means that changes are not likely to happen to them.…”

Section: Introductionmentioning

confidence: 99%

A Multimodal Biometric System using Global Features for Identical Twins Identification

Mohammed

Shamsuddin

2018

Journal of Computer Science

View full text Add to dashboard Cite

Pattern recognition studies are currently focusing on twin's biometric identification. The system of twins' biometric Identification can potentially differentiate the individual's biometric pattern. With the new Unimodal biometric identification, identical twins are precisely and reliably identified, with well exposure of certain traits. However, it is much more challenging to identify identical twins as they share so many similarities between them, as opposed to identifying the non-twins. Therefore, this study proposes the use of more than one biometric trait with global features. Pattern recognition application includes extracting and selecting meaningful features and this has brought to the key question in twin handwriting-fingerprint identification: How to obtain features from many writing styles and shapes of twin handwritingfingerprint in order that the reflection of the right person between twins can be obtained. Global with Aspect United Moment Invariant for the extractions of global feature using the identical twin multi-biometric identification is thus proposed by this study.

show abstract

Double Trouble: Differentiating Identical Twins by Face Recognition

Cited by 33 publications

References 11 publications

Fine-grained face verification: Dataset and baseline results

Fine-grained face verification: Dataset and baseline results

Lessons from collecting a million biometric samples

A Multimodal Biometric System using Global Features for Identical Twins Identification

Contact Info

Product

Resources

About