İNSANLARIN YAŞ TAHMİN YETENEĞİ ve TAHMİNLERİNİ ETKİLEYEN FAKTÖRLER
Yıl 2024,
Sayı: 49, 38 - 46, 31.12.2024
Nurdan Sezgin
,
Yeşim Tunç
Öz
Yüz görüntülerinden yaş tahminine odaklanan çalışmaların sayısı her geçen gün artmaktadır. Bu çalışmalar büyük ölçüde otomatik sistemler tarafından gerçekleştirilmektedir. Bu teknikler daha iyi sonuçlar vermiş olsa da henüz insan yapımı kadar başarılı tahmin seviyelerine ulaşamamıştır. İnsanların tahminlerini etkileyen önemli karar verme değişkenlerini belirleyebilmek, bu sistemleri geliştirebilecek şeylerden biridir. Bu çalışmanın amacı, insan gözlemcilerin tahminlerinin başarı oranını incelemek ve bu tahminleri neyin etkilediğine dikkat çekmektir. Bu çalışmada bir yaş tahmin anketi sunulmuştur. İnsanlara yaş tahmini konusunda kendilerine güvenip güvenmedikleri ve tahminlerini hangi faktörlerin etkilediği sorulmuştur. Katılımcılara Google Forms kullanılarak oluşturulmuş bir çevrimiçi anket sunulmuştur. Çalışmaya 66 erkek ve 157 kadın olmak üzere toplam 223 kişi katılmıştır. Genel olarak 12 görüntüden 5’i doğru tahmin edilmiş, 7’si yanlış tahmin edilmiştir. Tüm katılımcıların yaşları (12 kişinin yüz görüntüleri) ortalama %30,08 oranında doğru tahmin edilmiştir. Katılımcıların çoğunluğu (%77,6) kendi tahminlerine bir düzeyde güvendiklerini ve genel olarak doğru tahminlerde bulunduklarını ifade etmişlerdir. Faktör belirleme sıklığı incelendiğinde, katılımcıların çoğunluğunun (%65,17) yüzlerdeki kırışıklıklara odaklandığı görülmüştür (çalışma genel yüz, gözler ve ağza yer vermektedir.). Gelecekteki çalışmaların yaş tahminini etkileyen faktör sayısını artırarak ve daha fazla makine öğrenimi çalışması dahil ederek daha iyi sonuçlar vermesi beklenmektedir.
Kaynakça
- Alexis, A.F., Grimes, P., Boyd, C., Downie, J., Drinkwater, A., Garcia, J.K. et al. (2019). Racial and ethnic differences in self-assessed facial aging in women: results from a multinational study. Dermatol Surg. 45(12):1635-1648. doi: 10.1097/DSS.0000000000002237
- Anguluu, R., Tapamo, J. R. & Adewumi A. O. (2018). Age estimation via face images: A survey. EURASIP J on Image and Video Processing, 42:1-35. https://doi.org/10.1186/s13640-018-0278-6
- Blanpain, C. & Fuchs, E. (2006). Epidermal stem cells of the skin. Annu Rev Cell Dev Biol, 22:339–373. https://doi.org/10.1146/annurev.cellbio.22.010305.104357
- Coleman, S.R., Grover, R. (2006). The anatomy of the aging face: volume loss and changes in 3-dimensional topography. Aesthet Surg. 26(1S):S4-S9. https://doi.org/10.1016/j.asj.2005.09.012
- Geng, X., Smith-Miles, K. & Zhou, Z. H. (2008). Facial age estimation by nonlinear aging pattern subspace. Proceedings of the 16th ACM International Conference on Multimedia, Oct, pp. 721-724. https://doi.org/10.1145/1459359.1459469
- Guo, G. & Wang, X. (2012). A study on human age estimation under facial expression changes. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (IEEE, Providence), pp. 2547–2553. doi: 10.1109/CVPR.2012.6247972
- Gupta, M.A., Gilchrest, B.A. (2005). Psychosocial aspects of aging skin. Dermatol Clin. 23(4):643-648. doi: 10.1016/j.det.2005.05.012
- Han, H., Otto, C. & Jain, A. K. (2013). Age estimation from face images: Human vs. machine performance. In 2013 International Conference on Biometrics (ICB), IEEE, pp. 1-8. doi: 10.1109/ICB.2013.6613022
- Jana, R., Datta, D. & Saha, R. (2013). Age group estimation using face features. Int J Engineering and Innovative Technology, 3(2):130-134.
- Jana, R., Datta, D. & Saha, R. (2015). Age estimation from face image using wrinkle features. Science Direct, 46:1754-1761. https://doi.org/10.1016/j.procs.2015.02.126
- Kumar, N., Berg, A., Belhumeur, P. & Nayar, S. (2011). Describable visual attributes for face verification and image search. IEEE Trans. PAMI, 33(10):1962–1977. doi: 10.1109/TPAMI.2011.48
- Lanitis, A., Draganova, C. & Christodoulou. (2004). Comparing different classifiers for automatic age estimation. IEEE Trans Syst Man Cybern. B, Cybern, 34(4):621-628. doi: 10.1109/TSMCB.2003.817091
- Nguyen, D. T., Cho, S. R., Shin, K. Y., Bang, J. W. & Park, K. R. (2014). Comparative study of human age estimation with or without preclassification of gender and facial expression. Sci. World J, pp. 1–15. https://doi.org/10.1155/2014/905269
- Reilly, M.J., Tomsic, J.A., Fernandez, S.J., Davison, S.P. (2015). Effect of facial rejuvenation surgery on perceived attractiveness, femininity, and personality. JAMA Facial Plas Surg. 17(3):202-207. https://doi.org/10.1001/jamafacial.2015.015
- Rossi, A.M., Eviatar, J., Green, J.B., Anolik, R., Eidelman, M., Keaney, T.C. et al. (2017). Signs of facial aging in men in a diverse, multinational study: timing and preventive behaviors. Dermatol Surg. 43(Suppl 2):S210-S220. doi: 10.1097/DSS.0000000000001293
- Sezgin, N., Karadayı, Ş. & Karadayı, B. (2017). Görgü tanıklığında yaş tahmininin güvenilirliği. Ata Üni Sos Bil Ens Derg, 58:203-216.
- Swift, A., Liew, S., Weinkle, S., Garcia, J.K., Silberberg, M.B. (2021). The facial aging process from the “Inside Out”. Aesthetic Surgery Journal, 41(10):1107-1119. https://doi.org/10.1093/asj/sjaa339
- Zhang, S. & Duan, E. (2018). Fighting against skin aging: The way from bench to bedside. Cell Transplantation, 27(5):729-738. doi: 10.1177/0963689717725755
- Zimbler, M. S., Kokosa, M. S. & Thomas, J. R. (2001). Anatomy and pathophysiology of facial aging. Facial Plast. Surg. Clin. N. Am., 9:179–187. https://doi.org/10.1016/S1064-7406(23)00393-0
Human age estimation ability and factors affect the estimation
Yıl 2024,
Sayı: 49, 38 - 46, 31.12.2024
Nurdan Sezgin
,
Yeşim Tunç
Öz
Number of studies that are focused on estimating age from facial images are increasing every day. These studies are performed largely by automatic systems. Altough these techniques have given better results, they have not reached successful estimation levels as human made, yet. Being able to identify the significant decision-making variables that influence people's estimations is one of the things that can improve these systems. The aim of this study is to examine the success rate of human observers' estimations and to draw attention to what affects those estimations. In this study an age estimation survey was offered; people were asked whether they trust themselves about age estimation and which factors affect their estimations. Participants have been provided with an online survey created using Google Forms. A total of 223 people participated in the study, 66 male and 157 female. In general total 5 images were estimated correctly out of 12, 7 were estimated incorrectly. The ages of all participants (face images of 12 individuals) were estimated correctly with an average of 30.08%. The majority of participants (77,6%) claim to trust their judgement on some level and to make correct estimations overall. When the frequency of factor designation was examined, it was discovered that the majority of participants (65,17%) were focused on the wrinkles on faces (the study includes general face, eyes and mouth.). It is expected that future studies would yield improved results by increasing the number of factors affecting age estimation and including more machine learning studies.
Etik Beyan
Kütahya Health Sciences University Non-invasive Clinical Research Ethics Committee approved the study ethic protocol. This work has been carried out in accordance with the Helsinki Declaration.
Kaynakça
- Alexis, A.F., Grimes, P., Boyd, C., Downie, J., Drinkwater, A., Garcia, J.K. et al. (2019). Racial and ethnic differences in self-assessed facial aging in women: results from a multinational study. Dermatol Surg. 45(12):1635-1648. doi: 10.1097/DSS.0000000000002237
- Anguluu, R., Tapamo, J. R. & Adewumi A. O. (2018). Age estimation via face images: A survey. EURASIP J on Image and Video Processing, 42:1-35. https://doi.org/10.1186/s13640-018-0278-6
- Blanpain, C. & Fuchs, E. (2006). Epidermal stem cells of the skin. Annu Rev Cell Dev Biol, 22:339–373. https://doi.org/10.1146/annurev.cellbio.22.010305.104357
- Coleman, S.R., Grover, R. (2006). The anatomy of the aging face: volume loss and changes in 3-dimensional topography. Aesthet Surg. 26(1S):S4-S9. https://doi.org/10.1016/j.asj.2005.09.012
- Geng, X., Smith-Miles, K. & Zhou, Z. H. (2008). Facial age estimation by nonlinear aging pattern subspace. Proceedings of the 16th ACM International Conference on Multimedia, Oct, pp. 721-724. https://doi.org/10.1145/1459359.1459469
- Guo, G. & Wang, X. (2012). A study on human age estimation under facial expression changes. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (IEEE, Providence), pp. 2547–2553. doi: 10.1109/CVPR.2012.6247972
- Gupta, M.A., Gilchrest, B.A. (2005). Psychosocial aspects of aging skin. Dermatol Clin. 23(4):643-648. doi: 10.1016/j.det.2005.05.012
- Han, H., Otto, C. & Jain, A. K. (2013). Age estimation from face images: Human vs. machine performance. In 2013 International Conference on Biometrics (ICB), IEEE, pp. 1-8. doi: 10.1109/ICB.2013.6613022
- Jana, R., Datta, D. & Saha, R. (2013). Age group estimation using face features. Int J Engineering and Innovative Technology, 3(2):130-134.
- Jana, R., Datta, D. & Saha, R. (2015). Age estimation from face image using wrinkle features. Science Direct, 46:1754-1761. https://doi.org/10.1016/j.procs.2015.02.126
- Kumar, N., Berg, A., Belhumeur, P. & Nayar, S. (2011). Describable visual attributes for face verification and image search. IEEE Trans. PAMI, 33(10):1962–1977. doi: 10.1109/TPAMI.2011.48
- Lanitis, A., Draganova, C. & Christodoulou. (2004). Comparing different classifiers for automatic age estimation. IEEE Trans Syst Man Cybern. B, Cybern, 34(4):621-628. doi: 10.1109/TSMCB.2003.817091
- Nguyen, D. T., Cho, S. R., Shin, K. Y., Bang, J. W. & Park, K. R. (2014). Comparative study of human age estimation with or without preclassification of gender and facial expression. Sci. World J, pp. 1–15. https://doi.org/10.1155/2014/905269
- Reilly, M.J., Tomsic, J.A., Fernandez, S.J., Davison, S.P. (2015). Effect of facial rejuvenation surgery on perceived attractiveness, femininity, and personality. JAMA Facial Plas Surg. 17(3):202-207. https://doi.org/10.1001/jamafacial.2015.015
- Rossi, A.M., Eviatar, J., Green, J.B., Anolik, R., Eidelman, M., Keaney, T.C. et al. (2017). Signs of facial aging in men in a diverse, multinational study: timing and preventive behaviors. Dermatol Surg. 43(Suppl 2):S210-S220. doi: 10.1097/DSS.0000000000001293
- Sezgin, N., Karadayı, Ş. & Karadayı, B. (2017). Görgü tanıklığında yaş tahmininin güvenilirliği. Ata Üni Sos Bil Ens Derg, 58:203-216.
- Swift, A., Liew, S., Weinkle, S., Garcia, J.K., Silberberg, M.B. (2021). The facial aging process from the “Inside Out”. Aesthetic Surgery Journal, 41(10):1107-1119. https://doi.org/10.1093/asj/sjaa339
- Zhang, S. & Duan, E. (2018). Fighting against skin aging: The way from bench to bedside. Cell Transplantation, 27(5):729-738. doi: 10.1177/0963689717725755
- Zimbler, M. S., Kokosa, M. S. & Thomas, J. R. (2001). Anatomy and pathophysiology of facial aging. Facial Plast. Surg. Clin. N. Am., 9:179–187. https://doi.org/10.1016/S1064-7406(23)00393-0