Recognition of identical twins using fusion of various facial feature extractors

Afaneh, Ayman; Noroozi, Fatemeh; Toygar, Önsen

doi:10.1186/s13640-017-0231-0

Cited by 18 publications

(7 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several studies have aimed to implement multi-model face recognition systems to gain optimum use of diverse information in a face image [137][138][139]. Several studies have made efforts to perform fusion of multiple descriptors across face [140][141][142]. These systems show that despite the possibility of increased computational complexity, the multi-model systems can yield positive results.…”

Section: Multi-model Face Recognitionmentioning

confidence: 99%

Deep-learned faces: a survey

Arachchilage

Izquierdo

2020

J Image Video Proc.

View full text Add to dashboard Cite

Deep learning technology has enabled successful modeling of complex facial features when high-quality images are available. Nonetheless, accurate modeling and recognition of human faces in real-world scenarios “on the wild” or under adverse conditions remains an open problem. Consequently, a plethora of novel deep network architectures addressing issues related to low-quality images, varying pose, illumination changes, emotional expressions, etc., have been proposed and studied over the last few years.This survey presents a comprehensive analysis of the latest developments in the field. A conventional deep face recognition system entails several main components: deep network, optimization loss function, classification algorithm, and train data collection. Aiming at providing a complete and comprehensive study of such complex frameworks, this paper first discusses the evolution of related network architectures. Next, a comparative analysis of loss functions, classification algorithms, and face datasets is given. Then, a comparative study of state-of-the-art face recognition systems is presented. Here, the performance of the systems is discussed using three benchmarking datasets with increasing degrees of complexity. Furthermore, an experimental study was conducted to compare several openly accessible face recognition frameworks in terms of recognition accuracy and speed.

show abstract

Section: Multi-model Face Recognitionmentioning

confidence: 99%

Deep-learned faces: a survey

Arachchilage

Izquierdo

2020

J Image Video Proc.

View full text Add to dashboard Cite

show abstract

“…Different studies have been performed to distinguish identical twins using discriminant biometric traits such as face (Afaneh, Noroozi, & Toygar, 2017), fingerprint, palmprint, ear, and iris. It is stated in Jain, Prabhakar, and Pankanti (2002) that the identical twin fingerprints have a large class correlation.…”

Section: Related Workmentioning

confidence: 99%

On the use of ear and profile faces for distinguishing identical twins and nontwins

2019

Self Cite

View full text Add to dashboard Cite

This study aims to measure the efficiency of ear and profile face in distinguishing identical twins under identification and verification modes. In addition, to distinguish identical twins by ear and profile face separately, we propose to fuse these traits with all possible binary combinations of left ear, left profile face, right ear, and right profile face. Fusion is implemented by score‐level fusion and decision‐level fusion techniques in the proposed method. Additionally, feature‐level fusion is used for comparison. All experiments in this paper are also implemented on nontwins individuals, and the recognition performance of twins and nontwins are compared. Local binary patterns, local phase quantization, and binarized statistical image features approaches are used as texture‐based descriptors for feature extraction process. Images under controlled and uncontrolled lighting are tested. Ear and profile images from ND‐TWINS‐2009‐2010 dataset are used in the experiments. The experimental results show that the proposed method is more accurate and reliable than using ear or profile face images separately. The performance of the proposed method for recognizing identical twins as recognition rate is 100% and 99.45%, and equal error rates are 0.54% and 1.63% in controlled and uncontrolled illumination conditions, respectively.

show abstract

“…There are two prime starting premises for craniofacial superimposition: (1) that the anatomy of the face is sufficiently different between individuals that one individual can be differentiated from another (faces are specific to individuals) and ( 2) skulls and faces belonging to different persons cannot be confused as being derived from the same person (skulls are specific to faces of individuals). Both of these items largely hold true when genetically unrelated individuals are considered, but there is a segment of the population where differentiation based on facial morphology alone is known to be much more difficult (i.e., for genetically identical twins, same sex siblings, and occasional doppelgängers) [16][17][18][19][20]. Here, it is important to note that exceptions to the starting premises may apply as much to skull morphology as they do to facial characteristics, but data concerning the distinctiveness of skulls-as the specific subject matter-are much more sparse than for faces [16][17][18][19][20].…”

Section: Introductionmentioning

confidence: 99%

“…Both of these items largely hold true when genetically unrelated individuals are considered, but there is a segment of the population where differentiation based on facial morphology alone is known to be much more difficult (i.e., for genetically identical twins, same sex siblings, and occasional doppelgängers) [16][17][18][19][20]. Here, it is important to note that exceptions to the starting premises may apply as much to skull morphology as they do to facial characteristics, but data concerning the distinctiveness of skulls-as the specific subject matter-are much more sparse than for faces [16][17][18][19][20]. In these discussions of human anatomy patterns, it should be noted that the ability to biometrically differentiate between faces or skulls also depends specifically on what variables are considered as the unit of comparison [18,[20][21][22][23][24][25].…”

Section: Introductionmentioning

confidence: 99%

“…Here, it is important to note that exceptions to the starting premises may apply as much to skull morphology as they do to facial characteristics, but data concerning the distinctiveness of skulls-as the specific subject matter-are much more sparse than for faces [16][17][18][19][20]. In these discussions of human anatomy patterns, it should be noted that the ability to biometrically differentiate between faces or skulls also depends specifically on what variables are considered as the unit of comparison [18,[20][21][22][23][24][25]. This factor yields a range of identification potencies for superimposition depending on which particular comparison criteria are chosen.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Craniofacial superimposition: a review of focus distance estimation methods and an extension to profile view photographs

et al. 2022

View full text Add to dashboard Cite

Craniofacial superimposition concerns the photographic overlay of skulls and faces, for skeletal identification. As a phased method that depends on photographic optics first and anatomical comparisons second, superimposition is strongly underpinned by the physics of light travel through glass lenses. So that the downstream (and dependent) anatomical evaluations are not thwarted or erroneous identification decisions risked, it is critical that the optical prerequisites for valid image comparisons are met. As focus distance sets the perspective, the focus distance used for skull photography must be matched to that used at face photography, so that anatomically comparable 1:1 images are obtained. In this paper, we review the pertinent camera optics that set these nonnegotiable fundamentals and review a recently proposed method for focus distance estimation. We go beyond the original method descriptions to explain the mathematical justification for the PerspectiveX algorithm and provide an extension to profile images. This enables the first scientifically grounded use of profile view (or partial profile view) photographs in craniofacial superimposition. Proof of concept is provided by multiple worked examples of the focus distance estimation for frontal and profile view images of three of the authors at known focus distances. This innovation (1) removes longstanding trial-and-error components of present-day superimposition methods, (2) provides the first systematic and complete optical basis for image comparison in craniofacial superimposition, and (3) will enable anatomical comparison standards to be established from a valid grassroots basis where complexities of camera vantage point are removed as interfering factors.

show abstract

Recognition of identical twins using fusion of various facial feature extractors

Cited by 18 publications

References 33 publications

Deep-learned faces: a survey

Deep-learned faces: a survey

On the use of ear and profile faces for distinguishing identical twins and nontwins

Craniofacial superimposition: a review of focus distance estimation methods and an extension to profile view photographs

Contact Info

Product

Resources

About