A new approach for the analysis of facial growth and age estimation: Iris ratio

Machado, Carlos Eduardo Palhares; Flores, María de Lourdes Morales; Lima, Laíse Nascimento Correia; Tinoco, Rachel Lima Ribeiro; Franco, Ademir; Bezerra, Ana Cristina Barreto; Evison, Martin; Guimarães, Marco Aurélio

doi:10.1371/journal.pone.0180330

Cited by 39 publications

(35 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…• Facial asymmetry is slightly more pronounced in males compared to females. This is due to a difference in growth patterns and facial proportions between males and females [27]. Moreover, the masticatory frequencies are significantly higher in males resulting in pronounced facial asymmetry for lower part of the face [28].…”

Section: Discussionmentioning

confidence: 99%

Facial Asymmetry-Based Anthropometric Differences between Gender and Ethnicity

et al. 2018

View full text Add to dashboard Cite

Bilateral facial asymmetry is frequently exhibited by humans but its combined evaluation across demographic traits including gender and ethnicity is still an open research problem. In this study we measure and evaluate facial asymmetry across gender and different ethnic groups and investigate the differences in asymmetric facial dimensions among the subjects from two public face datasets, the MORPH and FERET. To this end, we detect 28 facial asymmetric dimensions from each face image using an anthropometric technique. An exploratory analysis is then performed via a multiple linear regression model to determine the impact of gender and ethnicity on facial asymmetry. Post-hoc Tukey test has been used to validate the results of the proposed method. The results show that out of 28 asymmetric dimensions, females differ in 25 dimensions from males. African, Asian, Hispanic and other ethnic groups have asymmetric dimensions that differ significantly from those of Europeans. These findings could be important to certain applications like the design of facial fits, as well as guidelines for facial cosmetic surgeons. Lastly, we train a neural network classifier that employs asymmetric dimensions for gender and race classification. The experimental results show that our trained classifier outperforms the support vector machine (SVM) and k-nearest neighbors (kNN) classifiers.

show abstract

Section: Discussionmentioning

confidence: 99%

Facial Asymmetry-Based Anthropometric Differences between Gender and Ethnicity

et al. 2018

View full text Add to dashboard Cite

show abstract

“…This scaling factor was previously determined by size comparison of a reference anatomical structure measured from images and real persons. The iris diameter was used for this purpose, as it has previously been proved to be an adequate reference for facial image calibration . Considering that the average iris diameter in images was calculated to be around 50 pixels and that the maximum population value of the horizontal visible iris diameter (HVID) is described in specific literature as around 11.5 mm , a ratio of 4.35 px/mm was determined.…”

Section: Methodsmentioning

confidence: 99%

“…Since facial measurements have been correlated with several individual characteristics, FPA has found large applications in a number of scientific fields in which the analysis of faces on two‐dimensional images is of interest . In legal medicine and forensic science, in particular, different studies reported the possibility of using FPA to estimate the age of individuals , to predict their sex or ancestry , to simulate facial growth or age progression , as well as to support human identification by comparing captured facial images to reference ones, that is, forensic facial identification (FFI) .…”

mentioning

confidence: 99%

“…This was done in order to assess the robustness of the approaches with respect to the experience level of the examiner. Observed landmark dispersions were finally compared to clinical standards currently accepted in cephalometry, by converting pixel-based values to millimeters through iris ratio calibration (7,26,27). To our knowledge, this is the first time that the adapted, FPA-optimized landmark-positioning previously reported by Flores et al (28) has been evaluated in published literature.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Comparative Assessment of a Novel Photo‐Anthropometric Landmark‐Positioning Approach for the Analysis of Facial Structures on Two‐Dimensional Images

Flores

Machado

Gallidabino

et al. 2018

Journal of Forensic Sciences

View full text Add to dashboard Cite

Positioning landmarks in facial photo‐anthropometry (FPA) applications remains today a highly variable procedure, as traditional cephalometric definitions are used as guidelines. Herein, a novel landmark‐positioning approach, specifically adapted for FPA applications, is introduced and, in particular, assessed against the conventional cephalometric definitions for the analysis of 16 landmarks on ten frontal images by two groups of examiners (with and without professional knowledge of anatomy). Results showed that positioning reproducibility was significantly better using the novel method. Indeed, in contrast to the classic approach, very low landmark dispersions were observed for both groups of examiners, which were usually below the strictest clinical standards (i.e., 0.575 mm). Furthermore, the comparison between the two groups of examiners highlighted higher dispersion consistencies, which supported a higher robustness. Thus, the use of an adapted landmark‐positioning approach proved to be highly advantageous in FPA analysis and future work in this field should consider adopting similar methodologies.

show abstract

“…There exists a sizable amount of literature on recognition of age-separated face images, such as [24][25][26][27][28][29][30][31][32][33][34][35][36]. The existing methods can be categorized as generative or discriminative.…”

Section: Recognition and Retrieval Of Face Images Across Aging Variatmentioning

confidence: 99%

Demographic-Assisted Age-Invariant Face Recognition and Retrieval

et al. 2018

View full text Add to dashboard Cite

Demographic estimation of human face images involves estimation of age group, gender, and race, which finds many applications, such as access control, forensics, and surveillance. Demographic estimation can help in designing such algorithms which lead to better understanding of the facial aging process and face recognition. Such a study has two parts-demographic estimation and subsequent face recognition and retrieval. In this paper, first we extract facial-asymmetry-based demographic informative features to estimate the age group, gender, and race of a given face image. The demographic features are then used to recognize and retrieve face images. Comparison of the demographic estimates from a state-of-the-art algorithm and the proposed approach is also presented. Experimental results on two longitudinal face datasets, the MORPH II and FERET, show that the proposed approach can compete the existing methods to recognize face images across aging variations.

show abstract

A new approach for the analysis of facial growth and age estimation: Iris ratio

Cited by 39 publications

References 28 publications

Facial Asymmetry-Based Anthropometric Differences between Gender and Ethnicity

Facial Asymmetry-Based Anthropometric Differences between Gender and Ethnicity

Comparative Assessment of a Novel Photo‐Anthropometric Landmark‐Positioning Approach for the Analysis of Facial Structures on Two‐Dimensional Images

Demographic-Assisted Age-Invariant Face Recognition and Retrieval

Contact Info

Product

Resources

About