Cross-age effect in artificial neural networks: a study on facial age recognition bias in artificial neural networks

Download

index.pdf

Date

2019

Author

Gürsoy, Necati Çağatay

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

104
views

107
downloads

Simply put cross-age effect or own-age bias is the phenomenon that when guessing the age of individuals from their faces, it is claimed that the age of the individual who is guessing the facial age effects the guessing process and the effect is towards to the age of the one who is guessing. Previous studies on the phenomenon acknowledges that such bias exists and especially in forensics this bias can cause drastic faults. In our two-part study, firstly the phenomenon is investigated in humans to observe if such effect exists, then it is tested if the error could be reduced via utilizing convolutional neural networks on face images and classify the face images with respect to their ages. For human based experiment, participants have rated facial images and for neural network based experiment a convolutional neural network model have constructed and tested with same images. In human based experiments, a strong correlation between participants’ guesses and the real ages of the face images displayed. Correlation analysis yield that a positive relationship between error (guessed age – actual age) and objective distance (participant’s age – actual age) exists whereas almost zero correlation exists between error and perceived distance (participant’s age – guessed age). Neural network experiment yields that neural network’s age rating performance exceeded human performance. Moreover; it is claimed that with necessary pre- processing to the input data, cross-age effect can be deduced with neural networks and human error can be reduced significantly.

Subject Keywords

Face perception., Own-age bias, cross-age effect, artificial neural networks, facial age recognition, facial age memory.

URI

http://etd.lib.metu.edu.tr/upload/12623442/index.pdf
https://hdl.handle.net/11511/43979

Collections

Graduate School of Informatics, Thesis

Suggestions

OpenMETU
Core

Incremental Processing of Morphosyntax for Counterfactual Reasoning: An Eye-tracking Study with Turkish-speaking Children and Adults Aktepe, Semih Can; Özge, Duygu; Department of English Language Teaching (2022-9) This study aimed to investigate whether children as young as age four can incrementally use morphosyntactic cues for counterfactual reasoning at adult-like level. Therefore, in this study, we answered (i) when children can reason adult-like using counterfactuals and (ii) whether they can incrementally integrate the morphosyntax of counterfactuals in a language that encodes both the conditional and counterfactual meaning in concatenated verbal suffixes, Turkish. We conducted an eye-tracking experiment using ...
Fault detection and diagnosis in nonlinear dynamical systems Kılıç, Erdal; Leblebicioğlu, Mehmet Kemal; Department of Electrical and Electronics Engineering (2005) The aim of this study is to solve Fault Detection and Diagnosis (FDD) problems occurring in nonlinear dynamical systems by using model and knowledge-based FDD methods and to give a priority and a degree about faults. For this purpose, three model-based FDD approaches, called FDD by utilizing principal component analysis (PCA), system identification based FDD and inverse model based FDD are introduced. Performances of these approaches are tested on different nonlinear dynamical systems starting from simple t...
Investigating the social interactions between parents and young children during digital activities at home Konca, Ahmet Sami; Erden, Feyza; Department of Early Childhood Education (2019) The aim of this study is to investigate how children interact with parents during digital activities. Interaction of children with other individuals is essential for communication, negotiation, and for sharing. Digital technologies have become widespread throughout all areas of a child’s life. Therefore, this study aimed to focus on the digital activities of children and the interactions that emerged during these activities. Participant observation, pre and post interviews were used to collect data in the s...
Auditory-visual speech perception in three- and four-year-olds and its relationship to perceptual attunement and receptive vocabulary Erdener, Dogu; Burnham, Denis (Cambridge University Press (CUP), 2018-03-01) Despite the body of research on auditory-visual speech perception in infants and schoolchildren, development in the early childhood period remains relatively uncharted. In this study, English-speaking children between three and four years of age were investigated for: (i) the development of visual speech perception - lip-reading and visual influence in auditory-visual integration; (ii) the development of auditory speech perception and native language perceptual attunement; and (iii) the relationship between...
Face identification, gender and age groups classifications for semantic annotation videos Yaprakkaya, Gökhan; Çiçekli, Fehime Nihan; Department of Computer Engineering (2010) This thesis presents a robust face recognition method and a combination of methods for gender identification and age group classification for semantic annotation of videos. Local binary pattern histogram which has 256 bins and pixel intensity differences are used as extracted facial features for gender classification. DCT Mod2 features and edge detection results around facial landmarks are used as extracted facial features for age group classification. In gender classification module, a Random Trees classif...

Citation Formats

N. Ç. Gürsoy, “Cross-age effect in artificial neural networks: a study on facial age recognition bias in artificial neural networks,” Thesis (M.S.) -- Graduate School of Informatics. Cognitive Sciences., Middle East Technical University, 2019.